helcig commited on
Commit
df46cd6
·
verified ·
1 Parent(s): 89a35b8

Add files using upload-large-folder tool

Browse files
Files changed (41) hide show
  1. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/README.md +18 -0
  2. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/chat_template.jinja +109 -0
  3. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/config.json +39 -0
  4. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/generation_config.json +10 -0
  5. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/humming_online_quant_config.json +1135 -0
  6. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/model.safetensors.index.json +731 -0
  7. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/quantization_config.txt +589 -0
  8. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/special_tokens_map.json +17 -0
  9. humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/tokenizer_config.json +2063 -0
  10. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/README.md +18 -0
  11. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/added_tokens.json +28 -0
  12. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/chat_template.jinja +89 -0
  13. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/config.json +96 -0
  14. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/generation_config.json +13 -0
  15. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/humming_online_quant_config.json +580 -0
  16. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/merges.txt +0 -0
  17. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/model.safetensors.index.json +715 -0
  18. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/quantization_config.txt +309 -0
  19. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/special_tokens_map.json +25 -0
  20. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/tokenizer_config.json +239 -0
  21. humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/vocab.json +0 -0
  22. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/README.md +7 -0
  23. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/added_tokens.json +28 -0
  24. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/chat_template.jinja +89 -0
  25. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/config.json +96 -0
  26. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/generation_config.json +13 -0
  27. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/humming_online_quant_config.json +5 -0
  28. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/merges.txt +0 -0
  29. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/model.safetensors.index.json +715 -0
  30. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/quantization_config.txt +285 -0
  31. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/special_tokens_map.json +25 -0
  32. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/tokenizer_config.json +239 -0
  33. humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/vocab.json +0 -0
  34. humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/config.json +2 -863
  35. humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/humming_online_quant_config.json +517 -0
  36. humming/Qwen3-8B/ll_sha_bw8.16_8bit/config.json +68 -0
  37. humming/Qwen3-8B/ll_sha_bw8.16_8bit/generation_config.json +13 -0
  38. humming/Qwen3-8B/ll_sha_bw8.16_8bit/merges.txt +0 -0
  39. humming/Qwen3-8B/ll_sha_bw8.16_8bit/special_tokens_map.json +25 -0
  40. humming/Qwen3-8B/ll_sha_bw8.16_8bit/tokenizer_config.json +239 -0
  41. humming/Qwen3-8B/ll_sha_bw8.16_8bit/vocab.json +0 -0
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/README.md ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Quantized Model Checkpoint
2
+
3
+ **Base model:** meta-llama/Llama-3.3-70B-Instruct
4
+
5
+ **Average bitwidth:** 6.5537
6
+
7
+ **Sensitivity method:** shapley
8
+
9
+ **Constraints:**
10
+ - max_kl: 0.01
11
+ - min_eap: 0.985
12
+
13
+ **Metrics:**
14
+ - final_kl: 0.003260
15
+ - final_eap: 0.986861
16
+ - final_etl: 0.013139
17
+
18
+ See `quantization_config.txt` for full configuration details.
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "float16",
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 80,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "transformers_version": "4.57.3",
37
+ "use_cache": false,
38
+ "vocab_size": 128256
39
+ }
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "transformers_version": "4.57.3"
10
+ }
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/humming_online_quant_config.json ADDED
@@ -0,0 +1,1135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quant_method": "gptq",
3
+ "bits": 7,
4
+ "group_size": 128,
5
+ "dynamic": {
6
+ "+:model\\.layers\\.0\\.self_attn\\.q_proj": {
7
+ "bits": 8
8
+ },
9
+ "+:model\\.layers\\.0\\.self_attn\\.k_proj": {
10
+ "bits": 8
11
+ },
12
+ "+:model\\.layers\\.0\\.self_attn\\.o_proj": {
13
+ "bits": 5
14
+ },
15
+ "+:model\\.layers\\.0\\.mlp\\.gate_proj": {
16
+ "bits": 5
17
+ },
18
+ "+:model\\.layers\\.0\\.mlp\\.down_proj": {
19
+ "bits": 5
20
+ },
21
+ "+:model\\.layers\\.1\\.self_attn\\.q_proj": {
22
+ "bits": 8
23
+ },
24
+ "+:model\\.layers\\.1\\.self_attn\\.v_proj": {
25
+ "bits": 8
26
+ },
27
+ "+:model\\.layers\\.1\\.mlp\\.gate_proj": {
28
+ "bits": 5
29
+ },
30
+ "+:model\\.layers\\.1\\.mlp\\.up_proj": {
31
+ "bits": 5
32
+ },
33
+ "+:model\\.layers\\.1\\.mlp\\.down_proj": {
34
+ "bits": 5
35
+ },
36
+ "+:model\\.layers\\.2\\.self_attn\\.k_proj": {
37
+ "bits": 8
38
+ },
39
+ "+:model\\.layers\\.2\\.self_attn\\.v_proj": {
40
+ "bits": 5
41
+ },
42
+ "+:model\\.layers\\.2\\.self_attn\\.o_proj": {
43
+ "bits": 8
44
+ },
45
+ "+:model\\.layers\\.2\\.mlp\\.gate_proj": {
46
+ "bits": 4
47
+ },
48
+ "+:model\\.layers\\.2\\.mlp\\.up_proj": {
49
+ "bits": 6
50
+ },
51
+ "+:model\\.layers\\.2\\.mlp\\.down_proj": {
52
+ "bits": 5
53
+ },
54
+ "+:model\\.layers\\.3\\.self_attn\\.q_proj": {
55
+ "bits": 5
56
+ },
57
+ "+:model\\.layers\\.3\\.mlp\\.up_proj": {
58
+ "bits": 8
59
+ },
60
+ "+:model\\.layers\\.4\\.self_attn\\.q_proj": {
61
+ "bits": 8
62
+ },
63
+ "+:model\\.layers\\.4\\.self_attn\\.k_proj": {
64
+ "bits": 5
65
+ },
66
+ "+:model\\.layers\\.4\\.self_attn\\.v_proj": {
67
+ "bits": 8
68
+ },
69
+ "+:model\\.layers\\.4\\.self_attn\\.o_proj": {
70
+ "bits": 6
71
+ },
72
+ "+:model\\.layers\\.4\\.mlp\\.gate_proj": {
73
+ "bits": 5
74
+ },
75
+ "+:model\\.layers\\.4\\.mlp\\.down_proj": {
76
+ "bits": 5
77
+ },
78
+ "+:model\\.layers\\.5\\.self_attn\\.q_proj": {
79
+ "bits": 8
80
+ },
81
+ "+:model\\.layers\\.5\\.self_attn\\.k_proj": {
82
+ "bits": 5
83
+ },
84
+ "+:model\\.layers\\.5\\.self_attn\\.o_proj": {
85
+ "bits": 6
86
+ },
87
+ "+:model\\.layers\\.5\\.mlp\\.down_proj": {
88
+ "bits": 6
89
+ },
90
+ "+:model\\.layers\\.6\\.self_attn\\.q_proj": {
91
+ "bits": 6
92
+ },
93
+ "+:model\\.layers\\.6\\.self_attn\\.v_proj": {
94
+ "bits": 8
95
+ },
96
+ "+:model\\.layers\\.6\\.self_attn\\.o_proj": {
97
+ "bits": 5
98
+ },
99
+ "+:model\\.layers\\.6\\.mlp\\.gate_proj": {
100
+ "bits": 5
101
+ },
102
+ "+:model\\.layers\\.6\\.mlp\\.up_proj": {
103
+ "bits": 4
104
+ },
105
+ "+:model\\.layers\\.6\\.mlp\\.down_proj": {
106
+ "bits": 6
107
+ },
108
+ "+:model\\.layers\\.7\\.self_attn\\.v_proj": {
109
+ "bits": 6
110
+ },
111
+ "+:model\\.layers\\.7\\.mlp\\.gate_proj": {
112
+ "bits": 5
113
+ },
114
+ "+:model\\.layers\\.7\\.mlp\\.up_proj": {
115
+ "bits": 5
116
+ },
117
+ "+:model\\.layers\\.7\\.mlp\\.down_proj": {
118
+ "bits": 5
119
+ },
120
+ "+:model\\.layers\\.8\\.self_attn\\.q_proj": {
121
+ "bits": 8
122
+ },
123
+ "+:model\\.layers\\.8\\.self_attn\\.k_proj": {
124
+ "bits": 6
125
+ },
126
+ "+:model\\.layers\\.8\\.self_attn\\.v_proj": {
127
+ "bits": 8
128
+ },
129
+ "+:model\\.layers\\.8\\.self_attn\\.o_proj": {
130
+ "bits": 5
131
+ },
132
+ "+:model\\.layers\\.8\\.mlp\\.gate_proj": {
133
+ "bits": 5
134
+ },
135
+ "+:model\\.layers\\.8\\.mlp\\.up_proj": {
136
+ "bits": 5
137
+ },
138
+ "+:model\\.layers\\.8\\.mlp\\.down_proj": {
139
+ "bits": 5
140
+ },
141
+ "+:model\\.layers\\.9\\.self_attn\\.q_proj": {
142
+ "bits": 8
143
+ },
144
+ "+:model\\.layers\\.9\\.self_attn\\.k_proj": {
145
+ "bits": 8
146
+ },
147
+ "+:model\\.layers\\.9\\.self_attn\\.o_proj": {
148
+ "bits": 6
149
+ },
150
+ "+:model\\.layers\\.9\\.mlp\\.gate_proj": {
151
+ "bits": 4
152
+ },
153
+ "+:model\\.layers\\.9\\.mlp\\.up_proj": {
154
+ "bits": 5
155
+ },
156
+ "+:model\\.layers\\.9\\.mlp\\.down_proj": {
157
+ "bits": 5
158
+ },
159
+ "+:model\\.layers\\.10\\.self_attn\\.q_proj": {
160
+ "bits": 5
161
+ },
162
+ "+:model\\.layers\\.10\\.mlp\\.gate_proj": {
163
+ "bits": 6
164
+ },
165
+ "+:model\\.layers\\.10\\.mlp\\.down_proj": {
166
+ "bits": 5
167
+ },
168
+ "+:model\\.layers\\.11\\.self_attn\\.q_proj": {
169
+ "bits": 8
170
+ },
171
+ "+:model\\.layers\\.11\\.self_attn\\.k_proj": {
172
+ "bits": 6
173
+ },
174
+ "+:model\\.layers\\.11\\.self_attn\\.v_proj": {
175
+ "bits": 5
176
+ },
177
+ "+:model\\.layers\\.11\\.mlp\\.gate_proj": {
178
+ "bits": 5
179
+ },
180
+ "+:model\\.layers\\.11\\.mlp\\.up_proj": {
181
+ "bits": 5
182
+ },
183
+ "+:model\\.layers\\.11\\.mlp\\.down_proj": {
184
+ "bits": 5
185
+ },
186
+ "+:model\\.layers\\.12\\.self_attn\\.v_proj": {
187
+ "bits": 8
188
+ },
189
+ "+:model\\.layers\\.12\\.self_attn\\.o_proj": {
190
+ "bits": 8
191
+ },
192
+ "+:model\\.layers\\.12\\.mlp\\.gate_proj": {
193
+ "bits": 5
194
+ },
195
+ "+:model\\.layers\\.12\\.mlp\\.up_proj": {
196
+ "bits": 5
197
+ },
198
+ "+:model\\.layers\\.12\\.mlp\\.down_proj": {
199
+ "bits": 5
200
+ },
201
+ "+:model\\.layers\\.13\\.self_attn\\.q_proj": {
202
+ "bits": 5
203
+ },
204
+ "+:model\\.layers\\.13\\.self_attn\\.v_proj": {
205
+ "bits": 5
206
+ },
207
+ "+:model\\.layers\\.13\\.self_attn\\.o_proj": {
208
+ "bits": 5
209
+ },
210
+ "+:model\\.layers\\.13\\.mlp\\.gate_proj": {
211
+ "bits": 5
212
+ },
213
+ "+:model\\.layers\\.13\\.mlp\\.up_proj": {
214
+ "bits": 4
215
+ },
216
+ "+:model\\.layers\\.14\\.self_attn\\.q_proj": {
217
+ "bits": 8
218
+ },
219
+ "+:model\\.layers\\.14\\.self_attn\\.k_proj": {
220
+ "bits": 8
221
+ },
222
+ "+:model\\.layers\\.14\\.self_attn\\.v_proj": {
223
+ "bits": 8
224
+ },
225
+ "+:model\\.layers\\.14\\.self_attn\\.o_proj": {
226
+ "bits": 8
227
+ },
228
+ "+:model\\.layers\\.14\\.mlp\\.up_proj": {
229
+ "bits": 6
230
+ },
231
+ "+:model\\.layers\\.14\\.mlp\\.down_proj": {
232
+ "bits": 6
233
+ },
234
+ "+:model\\.layers\\.15\\.self_attn\\.k_proj": {
235
+ "bits": 5
236
+ },
237
+ "+:model\\.layers\\.15\\.self_attn\\.o_proj": {
238
+ "bits": 8
239
+ },
240
+ "+:model\\.layers\\.15\\.mlp\\.gate_proj": {
241
+ "bits": 6
242
+ },
243
+ "+:model\\.layers\\.15\\.mlp\\.up_proj": {
244
+ "bits": 6
245
+ },
246
+ "+:model\\.layers\\.15\\.mlp\\.down_proj": {
247
+ "bits": 5
248
+ },
249
+ "+:model\\.layers\\.16\\.self_attn\\.q_proj": {
250
+ "bits": 8
251
+ },
252
+ "+:model\\.layers\\.16\\.self_attn\\.k_proj": {
253
+ "bits": 5
254
+ },
255
+ "+:model\\.layers\\.16\\.mlp\\.gate_proj": {
256
+ "bits": 6
257
+ },
258
+ "+:model\\.layers\\.16\\.mlp\\.up_proj": {
259
+ "bits": 6
260
+ },
261
+ "+:model\\.layers\\.16\\.mlp\\.down_proj": {
262
+ "bits": 4
263
+ },
264
+ "+:model\\.layers\\.17\\.self_attn\\.q_proj": {
265
+ "bits": 8
266
+ },
267
+ "+:model\\.layers\\.17\\.self_attn\\.k_proj": {
268
+ "bits": 8
269
+ },
270
+ "+:model\\.layers\\.17\\.self_attn\\.v_proj": {
271
+ "bits": 8
272
+ },
273
+ "+:model\\.layers\\.17\\.mlp\\.gate_proj": {
274
+ "bits": 5
275
+ },
276
+ "+:model\\.layers\\.18\\.self_attn\\.k_proj": {
277
+ "bits": 5
278
+ },
279
+ "+:model\\.layers\\.18\\.self_attn\\.v_proj": {
280
+ "bits": 5
281
+ },
282
+ "+:model\\.layers\\.18\\.self_attn\\.o_proj": {
283
+ "bits": 6
284
+ },
285
+ "+:model\\.layers\\.18\\.mlp\\.up_proj": {
286
+ "bits": 8
287
+ },
288
+ "+:model\\.layers\\.18\\.mlp\\.down_proj": {
289
+ "bits": 8
290
+ },
291
+ "+:model\\.layers\\.19\\.self_attn\\.k_proj": {
292
+ "bits": 8
293
+ },
294
+ "+:model\\.layers\\.19\\.mlp\\.gate_proj": {
295
+ "bits": 6
296
+ },
297
+ "+:model\\.layers\\.19\\.mlp\\.down_proj": {
298
+ "bits": 5
299
+ },
300
+ "+:model\\.layers\\.20\\.self_attn\\.q_proj": {
301
+ "bits": 8
302
+ },
303
+ "+:model\\.layers\\.20\\.self_attn\\.k_proj": {
304
+ "bits": 6
305
+ },
306
+ "+:model\\.layers\\.20\\.self_attn\\.v_proj": {
307
+ "bits": 8
308
+ },
309
+ "+:model\\.layers\\.20\\.mlp\\.gate_proj": {
310
+ "bits": 5
311
+ },
312
+ "+:model\\.layers\\.20\\.mlp\\.up_proj": {
313
+ "bits": 6
314
+ },
315
+ "+:model\\.layers\\.20\\.mlp\\.down_proj": {
316
+ "bits": 5
317
+ },
318
+ "+:model\\.layers\\.21\\.self_attn\\.q_proj": {
319
+ "bits": 5
320
+ },
321
+ "+:model\\.layers\\.21\\.self_attn\\.k_proj": {
322
+ "bits": 5
323
+ },
324
+ "+:model\\.layers\\.21\\.self_attn\\.v_proj": {
325
+ "bits": 5
326
+ },
327
+ "+:model\\.layers\\.21\\.self_attn\\.o_proj": {
328
+ "bits": 4
329
+ },
330
+ "+:model\\.layers\\.21\\.mlp\\.gate_proj": {
331
+ "bits": 5
332
+ },
333
+ "+:model\\.layers\\.21\\.mlp\\.down_proj": {
334
+ "bits": 5
335
+ },
336
+ "+:model\\.layers\\.22\\.self_attn\\.q_proj": {
337
+ "bits": 6
338
+ },
339
+ "+:model\\.layers\\.22\\.self_attn\\.k_proj": {
340
+ "bits": 6
341
+ },
342
+ "+:model\\.layers\\.22\\.self_attn\\.o_proj": {
343
+ "bits": 5
344
+ },
345
+ "+:model\\.layers\\.22\\.mlp\\.gate_proj": {
346
+ "bits": 8
347
+ },
348
+ "+:model\\.layers\\.22\\.mlp\\.up_proj": {
349
+ "bits": 5
350
+ },
351
+ "+:model\\.layers\\.22\\.mlp\\.down_proj": {
352
+ "bits": 6
353
+ },
354
+ "+:model\\.layers\\.23\\.self_attn\\.q_proj": {
355
+ "bits": 6
356
+ },
357
+ "+:model\\.layers\\.23\\.self_attn\\.k_proj": {
358
+ "bits": 8
359
+ },
360
+ "+:model\\.layers\\.23\\.self_attn\\.v_proj": {
361
+ "bits": 8
362
+ },
363
+ "+:model\\.layers\\.23\\.mlp\\.up_proj": {
364
+ "bits": 6
365
+ },
366
+ "+:model\\.layers\\.24\\.self_attn\\.q_proj": {
367
+ "bits": 5
368
+ },
369
+ "+:model\\.layers\\.24\\.self_attn\\.k_proj": {
370
+ "bits": 8
371
+ },
372
+ "+:model\\.layers\\.24\\.self_attn\\.o_proj": {
373
+ "bits": 5
374
+ },
375
+ "+:model\\.layers\\.24\\.mlp\\.up_proj": {
376
+ "bits": 6
377
+ },
378
+ "+:model\\.layers\\.25\\.self_attn\\.q_proj": {
379
+ "bits": 8
380
+ },
381
+ "+:model\\.layers\\.25\\.self_attn\\.k_proj": {
382
+ "bits": 6
383
+ },
384
+ "+:model\\.layers\\.25\\.self_attn\\.v_proj": {
385
+ "bits": 8
386
+ },
387
+ "+:model\\.layers\\.25\\.self_attn\\.o_proj": {
388
+ "bits": 6
389
+ },
390
+ "+:model\\.layers\\.25\\.mlp\\.gate_proj": {
391
+ "bits": 6
392
+ },
393
+ "+:model\\.layers\\.25\\.mlp\\.up_proj": {
394
+ "bits": 6
395
+ },
396
+ "+:model\\.layers\\.25\\.mlp\\.down_proj": {
397
+ "bits": 8
398
+ },
399
+ "+:model\\.layers\\.26\\.self_attn\\.q_proj": {
400
+ "bits": 8
401
+ },
402
+ "+:model\\.layers\\.26\\.self_attn\\.k_proj": {
403
+ "bits": 5
404
+ },
405
+ "+:model\\.layers\\.26\\.self_attn\\.v_proj": {
406
+ "bits": 8
407
+ },
408
+ "+:model\\.layers\\.26\\.mlp\\.gate_proj": {
409
+ "bits": 8
410
+ },
411
+ "+:model\\.layers\\.26\\.mlp\\.down_proj": {
412
+ "bits": 6
413
+ },
414
+ "+:model\\.layers\\.27\\.self_attn\\.k_proj": {
415
+ "bits": 8
416
+ },
417
+ "+:model\\.layers\\.27\\.self_attn\\.v_proj": {
418
+ "bits": 5
419
+ },
420
+ "+:model\\.layers\\.27\\.self_attn\\.o_proj": {
421
+ "bits": 8
422
+ },
423
+ "+:model\\.layers\\.27\\.mlp\\.gate_proj": {
424
+ "bits": 8
425
+ },
426
+ "+:model\\.layers\\.27\\.mlp\\.down_proj": {
427
+ "bits": 6
428
+ },
429
+ "+:model\\.layers\\.28\\.self_attn\\.k_proj": {
430
+ "bits": 8
431
+ },
432
+ "+:model\\.layers\\.28\\.self_attn\\.o_proj": {
433
+ "bits": 8
434
+ },
435
+ "+:model\\.layers\\.28\\.mlp\\.gate_proj": {
436
+ "bits": 5
437
+ },
438
+ "+:model\\.layers\\.28\\.mlp\\.down_proj": {
439
+ "bits": 6
440
+ },
441
+ "+:model\\.layers\\.29\\.self_attn\\.q_proj": {
442
+ "bits": 6
443
+ },
444
+ "+:model\\.layers\\.29\\.self_attn\\.k_proj": {
445
+ "bits": 8
446
+ },
447
+ "+:model\\.layers\\.30\\.self_attn\\.q_proj": {
448
+ "bits": 8
449
+ },
450
+ "+:model\\.layers\\.30\\.self_attn\\.k_proj": {
451
+ "bits": 8
452
+ },
453
+ "+:model\\.layers\\.30\\.self_attn\\.o_proj": {
454
+ "bits": 8
455
+ },
456
+ "+:model\\.layers\\.30\\.mlp\\.gate_proj": {
457
+ "bits": 5
458
+ },
459
+ "+:model\\.layers\\.30\\.mlp\\.down_proj": {
460
+ "bits": 5
461
+ },
462
+ "+:model\\.layers\\.31\\.self_attn\\.q_proj": {
463
+ "bits": 5
464
+ },
465
+ "+:model\\.layers\\.31\\.self_attn\\.k_proj": {
466
+ "bits": 6
467
+ },
468
+ "+:model\\.layers\\.31\\.self_attn\\.o_proj": {
469
+ "bits": 5
470
+ },
471
+ "+:model\\.layers\\.31\\.mlp\\.up_proj": {
472
+ "bits": 8
473
+ },
474
+ "+:model\\.layers\\.31\\.mlp\\.down_proj": {
475
+ "bits": 5
476
+ },
477
+ "+:model\\.layers\\.32\\.self_attn\\.v_proj": {
478
+ "bits": 8
479
+ },
480
+ "+:model\\.layers\\.32\\.self_attn\\.o_proj": {
481
+ "bits": 6
482
+ },
483
+ "+:model\\.layers\\.32\\.mlp\\.gate_proj": {
484
+ "bits": 6
485
+ },
486
+ "+:model\\.layers\\.32\\.mlp\\.up_proj": {
487
+ "bits": 8
488
+ },
489
+ "+:model\\.layers\\.32\\.mlp\\.down_proj": {
490
+ "bits": 6
491
+ },
492
+ "+:model\\.layers\\.33\\.self_attn\\.q_proj": {
493
+ "bits": 6
494
+ },
495
+ "+:model\\.layers\\.33\\.self_attn\\.k_proj": {
496
+ "bits": 8
497
+ },
498
+ "+:model\\.layers\\.33\\.self_attn\\.v_proj": {
499
+ "bits": 8
500
+ },
501
+ "+:model\\.layers\\.33\\.self_attn\\.o_proj": {
502
+ "bits": 6
503
+ },
504
+ "+:model\\.layers\\.33\\.mlp\\.gate_proj": {
505
+ "bits": 6
506
+ },
507
+ "+:model\\.layers\\.33\\.mlp\\.down_proj": {
508
+ "bits": 5
509
+ },
510
+ "+:model\\.layers\\.34\\.self_attn\\.q_proj": {
511
+ "bits": 8
512
+ },
513
+ "+:model\\.layers\\.34\\.self_attn\\.v_proj": {
514
+ "bits": 8
515
+ },
516
+ "+:model\\.layers\\.34\\.self_attn\\.o_proj": {
517
+ "bits": 5
518
+ },
519
+ "+:model\\.layers\\.34\\.mlp\\.gate_proj": {
520
+ "bits": 6
521
+ },
522
+ "+:model\\.layers\\.35\\.self_attn\\.k_proj": {
523
+ "bits": 8
524
+ },
525
+ "+:model\\.layers\\.35\\.self_attn\\.v_proj": {
526
+ "bits": 8
527
+ },
528
+ "+:model\\.layers\\.35\\.mlp\\.gate_proj": {
529
+ "bits": 8
530
+ },
531
+ "+:model\\.layers\\.35\\.mlp\\.up_proj": {
532
+ "bits": 6
533
+ },
534
+ "+:model\\.layers\\.35\\.mlp\\.down_proj": {
535
+ "bits": 6
536
+ },
537
+ "+:model\\.layers\\.36\\.self_attn\\.k_proj": {
538
+ "bits": 8
539
+ },
540
+ "+:model\\.layers\\.36\\.self_attn\\.v_proj": {
541
+ "bits": 6
542
+ },
543
+ "+:model\\.layers\\.37\\.self_attn\\.k_proj": {
544
+ "bits": 5
545
+ },
546
+ "+:model\\.layers\\.37\\.self_attn\\.v_proj": {
547
+ "bits": 5
548
+ },
549
+ "+:model\\.layers\\.37\\.self_attn\\.o_proj": {
550
+ "bits": 8
551
+ },
552
+ "+:model\\.layers\\.37\\.mlp\\.up_proj": {
553
+ "bits": 6
554
+ },
555
+ "+:model\\.layers\\.37\\.mlp\\.down_proj": {
556
+ "bits": 4
557
+ },
558
+ "+:model\\.layers\\.38\\.self_attn\\.q_proj": {
559
+ "bits": 6
560
+ },
561
+ "+:model\\.layers\\.38\\.self_attn\\.v_proj": {
562
+ "bits": 5
563
+ },
564
+ "+:model\\.layers\\.38\\.mlp\\.gate_proj": {
565
+ "bits": 8
566
+ },
567
+ "+:model\\.layers\\.38\\.mlp\\.down_proj": {
568
+ "bits": 5
569
+ },
570
+ "+:model\\.layers\\.39\\.self_attn\\.k_proj": {
571
+ "bits": 6
572
+ },
573
+ "+:model\\.layers\\.39\\.self_attn\\.v_proj": {
574
+ "bits": 8
575
+ },
576
+ "+:model\\.layers\\.39\\.mlp\\.gate_proj": {
577
+ "bits": 8
578
+ },
579
+ "+:model\\.layers\\.39\\.mlp\\.up_proj": {
580
+ "bits": 8
581
+ },
582
+ "+:model\\.layers\\.40\\.self_attn\\.q_proj": {
583
+ "bits": 6
584
+ },
585
+ "+:model\\.layers\\.40\\.self_attn\\.k_proj": {
586
+ "bits": 8
587
+ },
588
+ "+:model\\.layers\\.40\\.self_attn\\.v_proj": {
589
+ "bits": 8
590
+ },
591
+ "+:model\\.layers\\.40\\.mlp\\.gate_proj": {
592
+ "bits": 6
593
+ },
594
+ "+:model\\.layers\\.40\\.mlp\\.up_proj": {
595
+ "bits": 8
596
+ },
597
+ "+:model\\.layers\\.40\\.mlp\\.down_proj": {
598
+ "bits": 8
599
+ },
600
+ "+:model\\.layers\\.41\\.self_attn\\.q_proj": {
601
+ "bits": 8
602
+ },
603
+ "+:model\\.layers\\.41\\.self_attn\\.v_proj": {
604
+ "bits": 8
605
+ },
606
+ "+:model\\.layers\\.41\\.mlp\\.gate_proj": {
607
+ "bits": 5
608
+ },
609
+ "+:model\\.layers\\.41\\.mlp\\.down_proj": {
610
+ "bits": 6
611
+ },
612
+ "+:model\\.layers\\.42\\.self_attn\\.q_proj": {
613
+ "bits": 6
614
+ },
615
+ "+:model\\.layers\\.42\\.self_attn\\.k_proj": {
616
+ "bits": 6
617
+ },
618
+ "+:model\\.layers\\.42\\.mlp\\.down_proj": {
619
+ "bits": 8
620
+ },
621
+ "+:model\\.layers\\.43\\.self_attn\\.q_proj": {
622
+ "bits": 5
623
+ },
624
+ "+:model\\.layers\\.43\\.self_attn\\.v_proj": {
625
+ "bits": 6
626
+ },
627
+ "+:model\\.layers\\.44\\.self_attn\\.q_proj": {
628
+ "bits": 8
629
+ },
630
+ "+:model\\.layers\\.44\\.self_attn\\.k_proj": {
631
+ "bits": 8
632
+ },
633
+ "+:model\\.layers\\.44\\.self_attn\\.v_proj": {
634
+ "bits": 8
635
+ },
636
+ "+:model\\.layers\\.44\\.self_attn\\.o_proj": {
637
+ "bits": 6
638
+ },
639
+ "+:model\\.layers\\.44\\.mlp\\.up_proj": {
640
+ "bits": 8
641
+ },
642
+ "+:model\\.layers\\.45\\.self_attn\\.k_proj": {
643
+ "bits": 8
644
+ },
645
+ "+:model\\.layers\\.45\\.self_attn\\.v_proj": {
646
+ "bits": 8
647
+ },
648
+ "+:model\\.layers\\.45\\.self_attn\\.o_proj": {
649
+ "bits": 8
650
+ },
651
+ "+:model\\.layers\\.45\\.mlp\\.gate_proj": {
652
+ "bits": 5
653
+ },
654
+ "+:model\\.layers\\.45\\.mlp\\.down_proj": {
655
+ "bits": 5
656
+ },
657
+ "+:model\\.layers\\.46\\.self_attn\\.k_proj": {
658
+ "bits": 6
659
+ },
660
+ "+:model\\.layers\\.46\\.self_attn\\.v_proj": {
661
+ "bits": 8
662
+ },
663
+ "+:model\\.layers\\.46\\.self_attn\\.o_proj": {
664
+ "bits": 8
665
+ },
666
+ "+:model\\.layers\\.46\\.mlp\\.gate_proj": {
667
+ "bits": 8
668
+ },
669
+ "+:model\\.layers\\.46\\.mlp\\.up_proj": {
670
+ "bits": 6
671
+ },
672
+ "+:model\\.layers\\.46\\.mlp\\.down_proj": {
673
+ "bits": 8
674
+ },
675
+ "+:model\\.layers\\.47\\.self_attn\\.k_proj": {
676
+ "bits": 6
677
+ },
678
+ "+:model\\.layers\\.47\\.self_attn\\.o_proj": {
679
+ "bits": 5
680
+ },
681
+ "+:model\\.layers\\.47\\.mlp\\.up_proj": {
682
+ "bits": 5
683
+ },
684
+ "+:model\\.layers\\.47\\.mlp\\.down_proj": {
685
+ "bits": 5
686
+ },
687
+ "+:model\\.layers\\.48\\.self_attn\\.q_proj": {
688
+ "bits": 8
689
+ },
690
+ "+:model\\.layers\\.48\\.self_attn\\.k_proj": {
691
+ "bits": 8
692
+ },
693
+ "+:model\\.layers\\.48\\.self_attn\\.v_proj": {
694
+ "bits": 8
695
+ },
696
+ "+:model\\.layers\\.48\\.self_attn\\.o_proj": {
697
+ "bits": 8
698
+ },
699
+ "+:model\\.layers\\.48\\.mlp\\.up_proj": {
700
+ "bits": 8
701
+ },
702
+ "+:model\\.layers\\.49\\.self_attn\\.q_proj": {
703
+ "bits": 4
704
+ },
705
+ "+:model\\.layers\\.49\\.self_attn\\.k_proj": {
706
+ "bits": 8
707
+ },
708
+ "+:model\\.layers\\.49\\.self_attn\\.v_proj": {
709
+ "bits": 6
710
+ },
711
+ "+:model\\.layers\\.49\\.self_attn\\.o_proj": {
712
+ "bits": 5
713
+ },
714
+ "+:model\\.layers\\.49\\.mlp\\.gate_proj": {
715
+ "bits": 6
716
+ },
717
+ "+:model\\.layers\\.49\\.mlp\\.down_proj": {
718
+ "bits": 6
719
+ },
720
+ "+:model\\.layers\\.50\\.self_attn\\.v_proj": {
721
+ "bits": 5
722
+ },
723
+ "+:model\\.layers\\.50\\.mlp\\.gate_proj": {
724
+ "bits": 5
725
+ },
726
+ "+:model\\.layers\\.50\\.mlp\\.up_proj": {
727
+ "bits": 6
728
+ },
729
+ "+:model\\.layers\\.51\\.self_attn\\.q_proj": {
730
+ "bits": 5
731
+ },
732
+ "+:model\\.layers\\.51\\.self_attn\\.k_proj": {
733
+ "bits": 6
734
+ },
735
+ "+:model\\.layers\\.51\\.self_attn\\.v_proj": {
736
+ "bits": 5
737
+ },
738
+ "+:model\\.layers\\.51\\.mlp\\.gate_proj": {
739
+ "bits": 5
740
+ },
741
+ "+:model\\.layers\\.51\\.mlp\\.up_proj": {
742
+ "bits": 5
743
+ },
744
+ "+:model\\.layers\\.52\\.self_attn\\.q_proj": {
745
+ "bits": 5
746
+ },
747
+ "+:model\\.layers\\.52\\.self_attn\\.k_proj": {
748
+ "bits": 8
749
+ },
750
+ "+:model\\.layers\\.52\\.self_attn\\.v_proj": {
751
+ "bits": 8
752
+ },
753
+ "+:model\\.layers\\.52\\.mlp\\.gate_proj": {
754
+ "bits": 6
755
+ },
756
+ "+:model\\.layers\\.52\\.mlp\\.up_proj": {
757
+ "bits": 6
758
+ },
759
+ "+:model\\.layers\\.52\\.mlp\\.down_proj": {
760
+ "bits": 5
761
+ },
762
+ "+:model\\.layers\\.53\\.self_attn\\.q_proj": {
763
+ "bits": 8
764
+ },
765
+ "+:model\\.layers\\.53\\.self_attn\\.o_proj": {
766
+ "bits": 5
767
+ },
768
+ "+:model\\.layers\\.53\\.mlp\\.gate_proj": {
769
+ "bits": 6
770
+ },
771
+ "+:model\\.layers\\.53\\.mlp\\.up_proj": {
772
+ "bits": 5
773
+ },
774
+ "+:model\\.layers\\.53\\.mlp\\.down_proj": {
775
+ "bits": 5
776
+ },
777
+ "+:model\\.layers\\.54\\.self_attn\\.q_proj": {
778
+ "bits": 5
779
+ },
780
+ "+:model\\.layers\\.54\\.self_attn\\.o_proj": {
781
+ "bits": 8
782
+ },
783
+ "+:model\\.layers\\.54\\.mlp\\.gate_proj": {
784
+ "bits": 6
785
+ },
786
+ "+:model\\.layers\\.54\\.mlp\\.up_proj": {
787
+ "bits": 8
788
+ },
789
+ "+:model\\.layers\\.54\\.mlp\\.down_proj": {
790
+ "bits": 5
791
+ },
792
+ "+:model\\.layers\\.55\\.self_attn\\.q_proj": {
793
+ "bits": 6
794
+ },
795
+ "+:model\\.layers\\.55\\.self_attn\\.k_proj": {
796
+ "bits": 5
797
+ },
798
+ "+:model\\.layers\\.55\\.self_attn\\.v_proj": {
799
+ "bits": 8
800
+ },
801
+ "+:model\\.layers\\.55\\.self_attn\\.o_proj": {
802
+ "bits": 6
803
+ },
804
+ "+:model\\.layers\\.55\\.mlp\\.up_proj": {
805
+ "bits": 8
806
+ },
807
+ "+:model\\.layers\\.55\\.mlp\\.down_proj": {
808
+ "bits": 6
809
+ },
810
+ "+:model\\.layers\\.56\\.self_attn\\.q_proj": {
811
+ "bits": 8
812
+ },
813
+ "+:model\\.layers\\.56\\.self_attn\\.k_proj": {
814
+ "bits": 4
815
+ },
816
+ "+:model\\.layers\\.56\\.self_attn\\.v_proj": {
817
+ "bits": 5
818
+ },
819
+ "+:model\\.layers\\.56\\.mlp\\.gate_proj": {
820
+ "bits": 6
821
+ },
822
+ "+:model\\.layers\\.56\\.mlp\\.up_proj": {
823
+ "bits": 6
824
+ },
825
+ "+:model\\.layers\\.56\\.mlp\\.down_proj": {
826
+ "bits": 6
827
+ },
828
+ "+:model\\.layers\\.57\\.self_attn\\.q_proj": {
829
+ "bits": 5
830
+ },
831
+ "+:model\\.layers\\.57\\.self_attn\\.k_proj": {
832
+ "bits": 5
833
+ },
834
+ "+:model\\.layers\\.57\\.self_attn\\.v_proj": {
835
+ "bits": 5
836
+ },
837
+ "+:model\\.layers\\.57\\.mlp\\.gate_proj": {
838
+ "bits": 6
839
+ },
840
+ "+:model\\.layers\\.57\\.mlp\\.up_proj": {
841
+ "bits": 5
842
+ },
843
+ "+:model\\.layers\\.57\\.mlp\\.down_proj": {
844
+ "bits": 6
845
+ },
846
+ "+:model\\.layers\\.58\\.self_attn\\.q_proj": {
847
+ "bits": 5
848
+ },
849
+ "+:model\\.layers\\.58\\.self_attn\\.k_proj": {
850
+ "bits": 5
851
+ },
852
+ "+:model\\.layers\\.58\\.self_attn\\.o_proj": {
853
+ "bits": 5
854
+ },
855
+ "+:model\\.layers\\.58\\.mlp\\.gate_proj": {
856
+ "bits": 5
857
+ },
858
+ "+:model\\.layers\\.58\\.mlp\\.up_proj": {
859
+ "bits": 5
860
+ },
861
+ "+:model\\.layers\\.58\\.mlp\\.down_proj": {
862
+ "bits": 6
863
+ },
864
+ "+:model\\.layers\\.59\\.self_attn\\.q_proj": {
865
+ "bits": 5
866
+ },
867
+ "+:model\\.layers\\.59\\.self_attn\\.k_proj": {
868
+ "bits": 8
869
+ },
870
+ "+:model\\.layers\\.59\\.self_attn\\.v_proj": {
871
+ "bits": 8
872
+ },
873
+ "+:model\\.layers\\.59\\.self_attn\\.o_proj": {
874
+ "bits": 5
875
+ },
876
+ "+:model\\.layers\\.59\\.mlp\\.gate_proj": {
877
+ "bits": 6
878
+ },
879
+ "+:model\\.layers\\.59\\.mlp\\.up_proj": {
880
+ "bits": 5
881
+ },
882
+ "+:model\\.layers\\.60\\.mlp\\.gate_proj": {
883
+ "bits": 6
884
+ },
885
+ "+:model\\.layers\\.60\\.mlp\\.down_proj": {
886
+ "bits": 5
887
+ },
888
+ "+:model\\.layers\\.61\\.self_attn\\.v_proj": {
889
+ "bits": 8
890
+ },
891
+ "+:model\\.layers\\.61\\.mlp\\.down_proj": {
892
+ "bits": 5
893
+ },
894
+ "+:model\\.layers\\.62\\.self_attn\\.k_proj": {
895
+ "bits": 8
896
+ },
897
+ "+:model\\.layers\\.62\\.self_attn\\.v_proj": {
898
+ "bits": 8
899
+ },
900
+ "+:model\\.layers\\.62\\.self_attn\\.o_proj": {
901
+ "bits": 8
902
+ },
903
+ "+:model\\.layers\\.62\\.mlp\\.gate_proj": {
904
+ "bits": 5
905
+ },
906
+ "+:model\\.layers\\.62\\.mlp\\.up_proj": {
907
+ "bits": 6
908
+ },
909
+ "+:model\\.layers\\.63\\.self_attn\\.k_proj": {
910
+ "bits": 8
911
+ },
912
+ "+:model\\.layers\\.63\\.self_attn\\.v_proj": {
913
+ "bits": 6
914
+ },
915
+ "+:model\\.layers\\.63\\.mlp\\.gate_proj": {
916
+ "bits": 8
917
+ },
918
+ "+:model\\.layers\\.63\\.mlp\\.up_proj": {
919
+ "bits": 8
920
+ },
921
+ "+:model\\.layers\\.63\\.mlp\\.down_proj": {
922
+ "bits": 5
923
+ },
924
+ "+:model\\.layers\\.64\\.self_attn\\.q_proj": {
925
+ "bits": 8
926
+ },
927
+ "+:model\\.layers\\.64\\.self_attn\\.k_proj": {
928
+ "bits": 6
929
+ },
930
+ "+:model\\.layers\\.64\\.mlp\\.gate_proj": {
931
+ "bits": 6
932
+ },
933
+ "+:model\\.layers\\.65\\.self_attn\\.q_proj": {
934
+ "bits": 8
935
+ },
936
+ "+:model\\.layers\\.65\\.self_attn\\.k_proj": {
937
+ "bits": 8
938
+ },
939
+ "+:model\\.layers\\.65\\.self_attn\\.o_proj": {
940
+ "bits": 8
941
+ },
942
+ "+:model\\.layers\\.65\\.mlp\\.down_proj": {
943
+ "bits": 8
944
+ },
945
+ "+:model\\.layers\\.66\\.self_attn\\.q_proj": {
946
+ "bits": 8
947
+ },
948
+ "+:model\\.layers\\.66\\.self_attn\\.k_proj": {
949
+ "bits": 8
950
+ },
951
+ "+:model\\.layers\\.66\\.self_attn\\.v_proj": {
952
+ "bits": 8
953
+ },
954
+ "+:model\\.layers\\.66\\.self_attn\\.o_proj": {
955
+ "bits": 8
956
+ },
957
+ "+:model\\.layers\\.66\\.mlp\\.gate_proj": {
958
+ "bits": 8
959
+ },
960
+ "+:model\\.layers\\.66\\.mlp\\.up_proj": {
961
+ "bits": 8
962
+ },
963
+ "+:model\\.layers\\.66\\.mlp\\.down_proj": {
964
+ "bits": 8
965
+ },
966
+ "+:model\\.layers\\.67\\.self_attn\\.q_proj": {
967
+ "bits": 8
968
+ },
969
+ "+:model\\.layers\\.67\\.self_attn\\.k_proj": {
970
+ "bits": 8
971
+ },
972
+ "+:model\\.layers\\.67\\.mlp\\.down_proj": {
973
+ "bits": 6
974
+ },
975
+ "+:model\\.layers\\.68\\.self_attn\\.k_proj": {
976
+ "bits": 5
977
+ },
978
+ "+:model\\.layers\\.68\\.self_attn\\.o_proj": {
979
+ "bits": 5
980
+ },
981
+ "+:model\\.layers\\.68\\.mlp\\.up_proj": {
982
+ "bits": 8
983
+ },
984
+ "+:model\\.layers\\.68\\.mlp\\.down_proj": {
985
+ "bits": 6
986
+ },
987
+ "+:model\\.layers\\.69\\.self_attn\\.k_proj": {
988
+ "bits": 8
989
+ },
990
+ "+:model\\.layers\\.69\\.self_attn\\.v_proj": {
991
+ "bits": 8
992
+ },
993
+ "+:model\\.layers\\.69\\.mlp\\.gate_proj": {
994
+ "bits": 6
995
+ },
996
+ "+:model\\.layers\\.69\\.mlp\\.down_proj": {
997
+ "bits": 6
998
+ },
999
+ "+:model\\.layers\\.70\\.self_attn\\.k_proj": {
1000
+ "bits": 8
1001
+ },
1002
+ "+:model\\.layers\\.70\\.self_attn\\.o_proj": {
1003
+ "bits": 4
1004
+ },
1005
+ "+:model\\.layers\\.70\\.mlp\\.up_proj": {
1006
+ "bits": 8
1007
+ },
1008
+ "+:model\\.layers\\.70\\.mlp\\.down_proj": {
1009
+ "bits": 6
1010
+ },
1011
+ "+:model\\.layers\\.71\\.self_attn\\.q_proj": {
1012
+ "bits": 5
1013
+ },
1014
+ "+:model\\.layers\\.71\\.self_attn\\.k_proj": {
1015
+ "bits": 8
1016
+ },
1017
+ "+:model\\.layers\\.71\\.self_attn\\.v_proj": {
1018
+ "bits": 6
1019
+ },
1020
+ "+:model\\.layers\\.71\\.self_attn\\.o_proj": {
1021
+ "bits": 8
1022
+ },
1023
+ "+:model\\.layers\\.71\\.mlp\\.up_proj": {
1024
+ "bits": 6
1025
+ },
1026
+ "+:model\\.layers\\.71\\.mlp\\.down_proj": {
1027
+ "bits": 5
1028
+ },
1029
+ "+:model\\.layers\\.72\\.self_attn\\.k_proj": {
1030
+ "bits": 6
1031
+ },
1032
+ "+:model\\.layers\\.72\\.self_attn\\.v_proj": {
1033
+ "bits": 5
1034
+ },
1035
+ "+:model\\.layers\\.72\\.mlp\\.gate_proj": {
1036
+ "bits": 8
1037
+ },
1038
+ "+:model\\.layers\\.72\\.mlp\\.up_proj": {
1039
+ "bits": 6
1040
+ },
1041
+ "+:model\\.layers\\.73\\.self_attn\\.v_proj": {
1042
+ "bits": 8
1043
+ },
1044
+ "+:model\\.layers\\.73\\.mlp\\.gate_proj": {
1045
+ "bits": 6
1046
+ },
1047
+ "+:model\\.layers\\.73\\.mlp\\.up_proj": {
1048
+ "bits": 6
1049
+ },
1050
+ "+:model\\.layers\\.74\\.self_attn\\.k_proj": {
1051
+ "bits": 6
1052
+ },
1053
+ "+:model\\.layers\\.74\\.self_attn\\.v_proj": {
1054
+ "bits": 8
1055
+ },
1056
+ "+:model\\.layers\\.74\\.mlp\\.gate_proj": {
1057
+ "bits": 8
1058
+ },
1059
+ "+:model\\.layers\\.74\\.mlp\\.up_proj": {
1060
+ "bits": 6
1061
+ },
1062
+ "+:model\\.layers\\.75\\.self_attn\\.k_proj": {
1063
+ "bits": 6
1064
+ },
1065
+ "+:model\\.layers\\.75\\.self_attn\\.v_proj": {
1066
+ "bits": 5
1067
+ },
1068
+ "+:model\\.layers\\.75\\.self_attn\\.o_proj": {
1069
+ "bits": 5
1070
+ },
1071
+ "+:model\\.layers\\.75\\.mlp\\.gate_proj": {
1072
+ "bits": 8
1073
+ },
1074
+ "+:model\\.layers\\.75\\.mlp\\.up_proj": {
1075
+ "bits": 8
1076
+ },
1077
+ "+:model\\.layers\\.75\\.mlp\\.down_proj": {
1078
+ "bits": 6
1079
+ },
1080
+ "+:model\\.layers\\.76\\.self_attn\\.q_proj": {
1081
+ "bits": 6
1082
+ },
1083
+ "+:model\\.layers\\.76\\.self_attn\\.k_proj": {
1084
+ "bits": 8
1085
+ },
1086
+ "+:model\\.layers\\.76\\.self_attn\\.v_proj": {
1087
+ "bits": 8
1088
+ },
1089
+ "+:model\\.layers\\.76\\.mlp\\.up_proj": {
1090
+ "bits": 8
1091
+ },
1092
+ "+:model\\.layers\\.76\\.mlp\\.down_proj": {
1093
+ "bits": 6
1094
+ },
1095
+ "+:model\\.layers\\.77\\.self_attn\\.q_proj": {
1096
+ "bits": 8
1097
+ },
1098
+ "+:model\\.layers\\.77\\.self_attn\\.k_proj": {
1099
+ "bits": 8
1100
+ },
1101
+ "+:model\\.layers\\.77\\.self_attn\\.v_proj": {
1102
+ "bits": 6
1103
+ },
1104
+ "+:model\\.layers\\.77\\.self_attn\\.o_proj": {
1105
+ "bits": 8
1106
+ },
1107
+ "+:model\\.layers\\.77\\.mlp\\.gate_proj": {
1108
+ "bits": 6
1109
+ },
1110
+ "+:model\\.layers\\.78\\.self_attn\\.k_proj": {
1111
+ "bits": 8
1112
+ },
1113
+ "+:model\\.layers\\.78\\.self_attn\\.v_proj": {
1114
+ "bits": 5
1115
+ },
1116
+ "+:model\\.layers\\.78\\.self_attn\\.o_proj": {
1117
+ "bits": 8
1118
+ },
1119
+ "+:model\\.layers\\.78\\.mlp\\.gate_proj": {
1120
+ "bits": 6
1121
+ },
1122
+ "+:model\\.layers\\.79\\.self_attn\\.v_proj": {
1123
+ "bits": 6
1124
+ },
1125
+ "+:model\\.layers\\.79\\.self_attn\\.o_proj": {
1126
+ "bits": 8
1127
+ },
1128
+ "+:model\\.layers\\.79\\.mlp\\.gate_proj": {
1129
+ "bits": 8
1130
+ },
1131
+ "+:model\\.layers\\.79\\.mlp\\.up_proj": {
1132
+ "bits": 8
1133
+ }
1134
+ }
1135
+ }
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/model.safetensors.index.json ADDED
@@ -0,0 +1,731 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 70553706496,
4
+ "total_size": 141107412992
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00030-of-00030.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00030.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
198
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
199
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
200
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
201
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
202
+ "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
203
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
204
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
205
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
206
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
207
+ "model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors",
208
+ "model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
209
+ "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
210
+ "model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
211
+ "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
212
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
213
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
214
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
215
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
220
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
221
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
222
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
223
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
224
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
225
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
226
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
227
+ "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
228
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
229
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
230
+ "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
231
+ "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
232
+ "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
233
+ "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
234
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
235
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
236
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
237
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
238
+ "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
239
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
240
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
241
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
242
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
243
+ "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
244
+ "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
245
+ "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
246
+ "model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
247
+ "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
248
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
249
+ "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
250
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
251
+ "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
252
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
253
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
254
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
255
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
256
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
257
+ "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
258
+ "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
259
+ "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
260
+ "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
261
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
262
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
263
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
264
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
265
+ "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
266
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
267
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
268
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
269
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
270
+ "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
271
+ "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
272
+ "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
273
+ "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
274
+ "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
275
+ "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
276
+ "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
277
+ "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
278
+ "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
279
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
280
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
281
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
282
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
283
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
284
+ "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
285
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
286
+ "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
287
+ "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
288
+ "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
289
+ "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
290
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
291
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
292
+ "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
293
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
294
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
295
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
296
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
297
+ "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
298
+ "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
299
+ "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
300
+ "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
301
+ "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
302
+ "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
303
+ "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
304
+ "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
305
+ "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
306
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
307
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
308
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
309
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
310
+ "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
311
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
312
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
313
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
314
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
315
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors",
316
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
317
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
318
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
319
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
320
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
321
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
322
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
323
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
324
+ "model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors",
325
+ "model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
326
+ "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
327
+ "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
328
+ "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
329
+ "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
330
+ "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
331
+ "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
332
+ "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
333
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
334
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
335
+ "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
336
+ "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
337
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
338
+ "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
339
+ "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
340
+ "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
341
+ "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
342
+ "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
343
+ "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
344
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
345
+ "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
346
+ "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
347
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
348
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
349
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
350
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
351
+ "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
352
+ "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
353
+ "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
354
+ "model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
355
+ "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
356
+ "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
357
+ "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
358
+ "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
359
+ "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
360
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
361
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
362
+ "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
363
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
364
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
365
+ "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
366
+ "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
367
+ "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
368
+ "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
369
+ "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
370
+ "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
371
+ "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
372
+ "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
373
+ "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
374
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
375
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
376
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
377
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
378
+ "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
379
+ "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
380
+ "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
381
+ "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
382
+ "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
383
+ "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
384
+ "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
385
+ "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
386
+ "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
387
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
388
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
389
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
390
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
391
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
392
+ "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
393
+ "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
394
+ "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
395
+ "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
396
+ "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
397
+ "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
398
+ "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
399
+ "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
400
+ "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
401
+ "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
402
+ "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
403
+ "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
404
+ "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
405
+ "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
406
+ "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
407
+ "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
408
+ "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
409
+ "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
410
+ "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
411
+ "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
412
+ "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
413
+ "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
414
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
415
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
416
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
417
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
418
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
419
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
420
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
421
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
422
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
423
+ "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
424
+ "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
425
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
426
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
427
+ "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
428
+ "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
429
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
430
+ "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
431
+ "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
432
+ "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
433
+ "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
434
+ "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
435
+ "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
436
+ "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
437
+ "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
438
+ "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
439
+ "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
440
+ "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
441
+ "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
442
+ "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
443
+ "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
444
+ "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
445
+ "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
446
+ "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
447
+ "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
448
+ "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
449
+ "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
450
+ "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
451
+ "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
452
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
453
+ "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
454
+ "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
455
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
456
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
457
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
458
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
459
+ "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
460
+ "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
461
+ "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
462
+ "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
463
+ "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
464
+ "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
465
+ "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
466
+ "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
467
+ "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
468
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
469
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
470
+ "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
471
+ "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
472
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
473
+ "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
474
+ "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
475
+ "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
476
+ "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
477
+ "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
478
+ "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
479
+ "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
480
+ "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
481
+ "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
482
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
483
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
484
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
485
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
486
+ "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
487
+ "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
488
+ "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
489
+ "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
490
+ "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
491
+ "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
492
+ "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
493
+ "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
494
+ "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
495
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
496
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
497
+ "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
498
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
499
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
500
+ "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
501
+ "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
502
+ "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
503
+ "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
504
+ "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
505
+ "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
506
+ "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
507
+ "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
508
+ "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
509
+ "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
510
+ "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
511
+ "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
512
+ "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
513
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
514
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
515
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
516
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
517
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
518
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
519
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
520
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
521
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
522
+ "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
523
+ "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
524
+ "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
525
+ "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
526
+ "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
527
+ "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
528
+ "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
529
+ "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
530
+ "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
531
+ "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
532
+ "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
533
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
534
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
535
+ "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
536
+ "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
537
+ "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
538
+ "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
539
+ "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
540
+ "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
541
+ "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
542
+ "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
543
+ "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
544
+ "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
545
+ "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
546
+ "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
547
+ "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
548
+ "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
549
+ "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
550
+ "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
551
+ "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
552
+ "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
553
+ "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
554
+ "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
555
+ "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
556
+ "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
557
+ "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
558
+ "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
559
+ "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
560
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
561
+ "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
562
+ "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
563
+ "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
564
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
565
+ "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
566
+ "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
567
+ "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors",
568
+ "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
569
+ "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
570
+ "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
571
+ "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
572
+ "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
573
+ "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
574
+ "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
575
+ "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
576
+ "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
577
+ "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
578
+ "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
579
+ "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
580
+ "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
581
+ "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
582
+ "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
583
+ "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
584
+ "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
585
+ "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
586
+ "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
587
+ "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
588
+ "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
589
+ "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
590
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
591
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
592
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
593
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
594
+ "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
595
+ "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
596
+ "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
597
+ "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
598
+ "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
599
+ "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
600
+ "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
601
+ "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
602
+ "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
603
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
604
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
605
+ "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
606
+ "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
607
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
608
+ "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
609
+ "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
610
+ "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
611
+ "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
612
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors",
613
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
614
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
615
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
616
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
617
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
618
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
619
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
620
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
621
+ "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
622
+ "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
623
+ "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
624
+ "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
625
+ "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
626
+ "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
627
+ "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
628
+ "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
629
+ "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
630
+ "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
631
+ "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
632
+ "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
633
+ "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
634
+ "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
635
+ "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
636
+ "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
637
+ "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
638
+ "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
639
+ "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
640
+ "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
641
+ "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
642
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
643
+ "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
644
+ "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
645
+ "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
646
+ "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
647
+ "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
648
+ "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
649
+ "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
650
+ "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
651
+ "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
652
+ "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
653
+ "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
654
+ "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
655
+ "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
656
+ "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
657
+ "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
658
+ "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
659
+ "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
660
+ "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
661
+ "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
662
+ "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
663
+ "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
664
+ "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
665
+ "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
666
+ "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
667
+ "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
668
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
669
+ "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
670
+ "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
671
+ "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
672
+ "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
673
+ "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
674
+ "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
675
+ "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors",
676
+ "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
677
+ "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
678
+ "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
679
+ "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
680
+ "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
681
+ "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
682
+ "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
683
+ "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
684
+ "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
685
+ "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
686
+ "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
687
+ "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
688
+ "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
689
+ "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
690
+ "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
691
+ "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
692
+ "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
693
+ "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
694
+ "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
695
+ "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
696
+ "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
697
+ "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
698
+ "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
699
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
700
+ "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
701
+ "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
702
+ "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors",
703
+ "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
704
+ "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
705
+ "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
706
+ "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
707
+ "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
708
+ "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
709
+ "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
710
+ "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
711
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
712
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
713
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
714
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
715
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
716
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
717
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
718
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
719
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
720
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
721
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
722
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
723
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
724
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
725
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
726
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
727
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
728
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
729
+ "model.norm.weight": "model-00029-of-00030.safetensors"
730
+ }
731
+ }
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/quantization_config.txt ADDED
@@ -0,0 +1,589 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model: meta-llama/Llama-3.3-70B-Instruct
2
+ # Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4_5_6_7_8bit_asym_g128/Llama-3.3-70B-Instruct/4bit
3
+ # Sensitivity method: shapley
4
+ # Estimation method: permutation_separate
5
+ # Available bitwidths: [4, 5, 6, 7, 8]
6
+ # Bitwidth map: {4: 4.156, 5: 5.156, 6: 6.156, 7: 7.156, 8: 8.156}
7
+ #
8
+ # Mode: binary_search_constraint (measured)
9
+ # Constraint max_kl: 0.01
10
+ # Constraint min_eap: 0.985
11
+ # Weights: nll=0.0, kl=0.0, eap=1.0
12
+ #
13
+ # Average bitwidth: 6.5537
14
+ # Total params: 68451041280
15
+ # Total bits: 448605643080
16
+ # Final KL: 0.003260
17
+ # Final EAP: 0.986861
18
+ # Final ETL: 0.013139
19
+ # Satisfies constraints: True
20
+ # Solver calls: 9
21
+ # Evaluations: 9
22
+ #
23
+ # Bitwidth distribution:
24
+ # 8-bit: 146 layers (26.1%)
25
+ # 7-bit: 184 layers (32.9%)
26
+ # 6-bit: 104 layers (18.6%)
27
+ # 5-bit: 116 layers (20.7%)
28
+ # 4-bit: 10 layers (1.8%)
29
+ #
30
+ model.layers.0.self_attn.q_proj: 8
31
+ model.layers.0.self_attn.k_proj: 8
32
+ model.layers.0.self_attn.v_proj: 7
33
+ model.layers.0.self_attn.o_proj: 5
34
+ model.layers.0.mlp.gate_proj: 5
35
+ model.layers.0.mlp.up_proj: 7
36
+ model.layers.0.mlp.down_proj: 5
37
+ model.layers.1.self_attn.q_proj: 8
38
+ model.layers.1.self_attn.k_proj: 7
39
+ model.layers.1.self_attn.v_proj: 8
40
+ model.layers.1.self_attn.o_proj: 7
41
+ model.layers.1.mlp.gate_proj: 5
42
+ model.layers.1.mlp.up_proj: 5
43
+ model.layers.1.mlp.down_proj: 5
44
+ model.layers.2.self_attn.q_proj: 7
45
+ model.layers.2.self_attn.k_proj: 8
46
+ model.layers.2.self_attn.v_proj: 5
47
+ model.layers.2.self_attn.o_proj: 8
48
+ model.layers.2.mlp.gate_proj: 4
49
+ model.layers.2.mlp.up_proj: 6
50
+ model.layers.2.mlp.down_proj: 5
51
+ model.layers.3.self_attn.q_proj: 5
52
+ model.layers.3.self_attn.k_proj: 7
53
+ model.layers.3.self_attn.v_proj: 7
54
+ model.layers.3.self_attn.o_proj: 7
55
+ model.layers.3.mlp.gate_proj: 7
56
+ model.layers.3.mlp.up_proj: 8
57
+ model.layers.3.mlp.down_proj: 7
58
+ model.layers.4.self_attn.q_proj: 8
59
+ model.layers.4.self_attn.k_proj: 5
60
+ model.layers.4.self_attn.v_proj: 8
61
+ model.layers.4.self_attn.o_proj: 6
62
+ model.layers.4.mlp.gate_proj: 5
63
+ model.layers.4.mlp.up_proj: 7
64
+ model.layers.4.mlp.down_proj: 5
65
+ model.layers.5.self_attn.q_proj: 8
66
+ model.layers.5.self_attn.k_proj: 5
67
+ model.layers.5.self_attn.v_proj: 7
68
+ model.layers.5.self_attn.o_proj: 6
69
+ model.layers.5.mlp.gate_proj: 7
70
+ model.layers.5.mlp.up_proj: 7
71
+ model.layers.5.mlp.down_proj: 6
72
+ model.layers.6.self_attn.q_proj: 6
73
+ model.layers.6.self_attn.k_proj: 7
74
+ model.layers.6.self_attn.v_proj: 8
75
+ model.layers.6.self_attn.o_proj: 5
76
+ model.layers.6.mlp.gate_proj: 5
77
+ model.layers.6.mlp.up_proj: 4
78
+ model.layers.6.mlp.down_proj: 6
79
+ model.layers.7.self_attn.q_proj: 7
80
+ model.layers.7.self_attn.k_proj: 7
81
+ model.layers.7.self_attn.v_proj: 6
82
+ model.layers.7.self_attn.o_proj: 7
83
+ model.layers.7.mlp.gate_proj: 5
84
+ model.layers.7.mlp.up_proj: 5
85
+ model.layers.7.mlp.down_proj: 5
86
+ model.layers.8.self_attn.q_proj: 8
87
+ model.layers.8.self_attn.k_proj: 6
88
+ model.layers.8.self_attn.v_proj: 8
89
+ model.layers.8.self_attn.o_proj: 5
90
+ model.layers.8.mlp.gate_proj: 5
91
+ model.layers.8.mlp.up_proj: 5
92
+ model.layers.8.mlp.down_proj: 5
93
+ model.layers.9.self_attn.q_proj: 8
94
+ model.layers.9.self_attn.k_proj: 8
95
+ model.layers.9.self_attn.v_proj: 7
96
+ model.layers.9.self_attn.o_proj: 6
97
+ model.layers.9.mlp.gate_proj: 4
98
+ model.layers.9.mlp.up_proj: 5
99
+ model.layers.9.mlp.down_proj: 5
100
+ model.layers.10.self_attn.q_proj: 5
101
+ model.layers.10.self_attn.k_proj: 7
102
+ model.layers.10.self_attn.v_proj: 7
103
+ model.layers.10.self_attn.o_proj: 7
104
+ model.layers.10.mlp.gate_proj: 6
105
+ model.layers.10.mlp.up_proj: 7
106
+ model.layers.10.mlp.down_proj: 5
107
+ model.layers.11.self_attn.q_proj: 8
108
+ model.layers.11.self_attn.k_proj: 6
109
+ model.layers.11.self_attn.v_proj: 5
110
+ model.layers.11.self_attn.o_proj: 7
111
+ model.layers.11.mlp.gate_proj: 5
112
+ model.layers.11.mlp.up_proj: 5
113
+ model.layers.11.mlp.down_proj: 5
114
+ model.layers.12.self_attn.q_proj: 7
115
+ model.layers.12.self_attn.k_proj: 7
116
+ model.layers.12.self_attn.v_proj: 8
117
+ model.layers.12.self_attn.o_proj: 8
118
+ model.layers.12.mlp.gate_proj: 5
119
+ model.layers.12.mlp.up_proj: 5
120
+ model.layers.12.mlp.down_proj: 5
121
+ model.layers.13.self_attn.q_proj: 5
122
+ model.layers.13.self_attn.k_proj: 7
123
+ model.layers.13.self_attn.v_proj: 5
124
+ model.layers.13.self_attn.o_proj: 5
125
+ model.layers.13.mlp.gate_proj: 5
126
+ model.layers.13.mlp.up_proj: 4
127
+ model.layers.13.mlp.down_proj: 7
128
+ model.layers.14.self_attn.q_proj: 8
129
+ model.layers.14.self_attn.k_proj: 8
130
+ model.layers.14.self_attn.v_proj: 8
131
+ model.layers.14.self_attn.o_proj: 8
132
+ model.layers.14.mlp.gate_proj: 7
133
+ model.layers.14.mlp.up_proj: 6
134
+ model.layers.14.mlp.down_proj: 6
135
+ model.layers.15.self_attn.q_proj: 7
136
+ model.layers.15.self_attn.k_proj: 5
137
+ model.layers.15.self_attn.v_proj: 7
138
+ model.layers.15.self_attn.o_proj: 8
139
+ model.layers.15.mlp.gate_proj: 6
140
+ model.layers.15.mlp.up_proj: 6
141
+ model.layers.15.mlp.down_proj: 5
142
+ model.layers.16.self_attn.q_proj: 8
143
+ model.layers.16.self_attn.k_proj: 5
144
+ model.layers.16.self_attn.v_proj: 7
145
+ model.layers.16.self_attn.o_proj: 7
146
+ model.layers.16.mlp.gate_proj: 6
147
+ model.layers.16.mlp.up_proj: 6
148
+ model.layers.16.mlp.down_proj: 4
149
+ model.layers.17.self_attn.q_proj: 8
150
+ model.layers.17.self_attn.k_proj: 8
151
+ model.layers.17.self_attn.v_proj: 8
152
+ model.layers.17.self_attn.o_proj: 7
153
+ model.layers.17.mlp.gate_proj: 5
154
+ model.layers.17.mlp.up_proj: 7
155
+ model.layers.17.mlp.down_proj: 7
156
+ model.layers.18.self_attn.q_proj: 7
157
+ model.layers.18.self_attn.k_proj: 5
158
+ model.layers.18.self_attn.v_proj: 5
159
+ model.layers.18.self_attn.o_proj: 6
160
+ model.layers.18.mlp.gate_proj: 7
161
+ model.layers.18.mlp.up_proj: 8
162
+ model.layers.18.mlp.down_proj: 8
163
+ model.layers.19.self_attn.q_proj: 7
164
+ model.layers.19.self_attn.k_proj: 8
165
+ model.layers.19.self_attn.v_proj: 7
166
+ model.layers.19.self_attn.o_proj: 7
167
+ model.layers.19.mlp.gate_proj: 6
168
+ model.layers.19.mlp.up_proj: 7
169
+ model.layers.19.mlp.down_proj: 5
170
+ model.layers.20.self_attn.q_proj: 8
171
+ model.layers.20.self_attn.k_proj: 6
172
+ model.layers.20.self_attn.v_proj: 8
173
+ model.layers.20.self_attn.o_proj: 7
174
+ model.layers.20.mlp.gate_proj: 5
175
+ model.layers.20.mlp.up_proj: 6
176
+ model.layers.20.mlp.down_proj: 5
177
+ model.layers.21.self_attn.q_proj: 5
178
+ model.layers.21.self_attn.k_proj: 5
179
+ model.layers.21.self_attn.v_proj: 5
180
+ model.layers.21.self_attn.o_proj: 4
181
+ model.layers.21.mlp.gate_proj: 5
182
+ model.layers.21.mlp.up_proj: 7
183
+ model.layers.21.mlp.down_proj: 5
184
+ model.layers.22.self_attn.q_proj: 6
185
+ model.layers.22.self_attn.k_proj: 6
186
+ model.layers.22.self_attn.v_proj: 7
187
+ model.layers.22.self_attn.o_proj: 5
188
+ model.layers.22.mlp.gate_proj: 8
189
+ model.layers.22.mlp.up_proj: 5
190
+ model.layers.22.mlp.down_proj: 6
191
+ model.layers.23.self_attn.q_proj: 6
192
+ model.layers.23.self_attn.k_proj: 8
193
+ model.layers.23.self_attn.v_proj: 8
194
+ model.layers.23.self_attn.o_proj: 7
195
+ model.layers.23.mlp.gate_proj: 7
196
+ model.layers.23.mlp.up_proj: 6
197
+ model.layers.23.mlp.down_proj: 7
198
+ model.layers.24.self_attn.q_proj: 5
199
+ model.layers.24.self_attn.k_proj: 8
200
+ model.layers.24.self_attn.v_proj: 7
201
+ model.layers.24.self_attn.o_proj: 5
202
+ model.layers.24.mlp.gate_proj: 7
203
+ model.layers.24.mlp.up_proj: 6
204
+ model.layers.24.mlp.down_proj: 7
205
+ model.layers.25.self_attn.q_proj: 8
206
+ model.layers.25.self_attn.k_proj: 6
207
+ model.layers.25.self_attn.v_proj: 8
208
+ model.layers.25.self_attn.o_proj: 6
209
+ model.layers.25.mlp.gate_proj: 6
210
+ model.layers.25.mlp.up_proj: 6
211
+ model.layers.25.mlp.down_proj: 8
212
+ model.layers.26.self_attn.q_proj: 8
213
+ model.layers.26.self_attn.k_proj: 5
214
+ model.layers.26.self_attn.v_proj: 8
215
+ model.layers.26.self_attn.o_proj: 7
216
+ model.layers.26.mlp.gate_proj: 8
217
+ model.layers.26.mlp.up_proj: 7
218
+ model.layers.26.mlp.down_proj: 6
219
+ model.layers.27.self_attn.q_proj: 7
220
+ model.layers.27.self_attn.k_proj: 8
221
+ model.layers.27.self_attn.v_proj: 5
222
+ model.layers.27.self_attn.o_proj: 8
223
+ model.layers.27.mlp.gate_proj: 8
224
+ model.layers.27.mlp.up_proj: 7
225
+ model.layers.27.mlp.down_proj: 6
226
+ model.layers.28.self_attn.q_proj: 7
227
+ model.layers.28.self_attn.k_proj: 8
228
+ model.layers.28.self_attn.v_proj: 7
229
+ model.layers.28.self_attn.o_proj: 8
230
+ model.layers.28.mlp.gate_proj: 5
231
+ model.layers.28.mlp.up_proj: 7
232
+ model.layers.28.mlp.down_proj: 6
233
+ model.layers.29.self_attn.q_proj: 6
234
+ model.layers.29.self_attn.k_proj: 8
235
+ model.layers.29.self_attn.v_proj: 7
236
+ model.layers.29.self_attn.o_proj: 7
237
+ model.layers.29.mlp.gate_proj: 7
238
+ model.layers.29.mlp.up_proj: 7
239
+ model.layers.29.mlp.down_proj: 7
240
+ model.layers.30.self_attn.q_proj: 8
241
+ model.layers.30.self_attn.k_proj: 8
242
+ model.layers.30.self_attn.v_proj: 7
243
+ model.layers.30.self_attn.o_proj: 8
244
+ model.layers.30.mlp.gate_proj: 5
245
+ model.layers.30.mlp.up_proj: 7
246
+ model.layers.30.mlp.down_proj: 5
247
+ model.layers.31.self_attn.q_proj: 5
248
+ model.layers.31.self_attn.k_proj: 6
249
+ model.layers.31.self_attn.v_proj: 7
250
+ model.layers.31.self_attn.o_proj: 5
251
+ model.layers.31.mlp.gate_proj: 7
252
+ model.layers.31.mlp.up_proj: 8
253
+ model.layers.31.mlp.down_proj: 5
254
+ model.layers.32.self_attn.q_proj: 7
255
+ model.layers.32.self_attn.k_proj: 7
256
+ model.layers.32.self_attn.v_proj: 8
257
+ model.layers.32.self_attn.o_proj: 6
258
+ model.layers.32.mlp.gate_proj: 6
259
+ model.layers.32.mlp.up_proj: 8
260
+ model.layers.32.mlp.down_proj: 6
261
+ model.layers.33.self_attn.q_proj: 6
262
+ model.layers.33.self_attn.k_proj: 8
263
+ model.layers.33.self_attn.v_proj: 8
264
+ model.layers.33.self_attn.o_proj: 6
265
+ model.layers.33.mlp.gate_proj: 6
266
+ model.layers.33.mlp.up_proj: 7
267
+ model.layers.33.mlp.down_proj: 5
268
+ model.layers.34.self_attn.q_proj: 8
269
+ model.layers.34.self_attn.k_proj: 7
270
+ model.layers.34.self_attn.v_proj: 8
271
+ model.layers.34.self_attn.o_proj: 5
272
+ model.layers.34.mlp.gate_proj: 6
273
+ model.layers.34.mlp.up_proj: 7
274
+ model.layers.34.mlp.down_proj: 7
275
+ model.layers.35.self_attn.q_proj: 7
276
+ model.layers.35.self_attn.k_proj: 8
277
+ model.layers.35.self_attn.v_proj: 8
278
+ model.layers.35.self_attn.o_proj: 7
279
+ model.layers.35.mlp.gate_proj: 8
280
+ model.layers.35.mlp.up_proj: 6
281
+ model.layers.35.mlp.down_proj: 6
282
+ model.layers.36.self_attn.q_proj: 7
283
+ model.layers.36.self_attn.k_proj: 8
284
+ model.layers.36.self_attn.v_proj: 6
285
+ model.layers.36.self_attn.o_proj: 7
286
+ model.layers.36.mlp.gate_proj: 7
287
+ model.layers.36.mlp.up_proj: 7
288
+ model.layers.36.mlp.down_proj: 7
289
+ model.layers.37.self_attn.q_proj: 7
290
+ model.layers.37.self_attn.k_proj: 5
291
+ model.layers.37.self_attn.v_proj: 5
292
+ model.layers.37.self_attn.o_proj: 8
293
+ model.layers.37.mlp.gate_proj: 7
294
+ model.layers.37.mlp.up_proj: 6
295
+ model.layers.37.mlp.down_proj: 4
296
+ model.layers.38.self_attn.q_proj: 6
297
+ model.layers.38.self_attn.k_proj: 7
298
+ model.layers.38.self_attn.v_proj: 5
299
+ model.layers.38.self_attn.o_proj: 7
300
+ model.layers.38.mlp.gate_proj: 8
301
+ model.layers.38.mlp.up_proj: 7
302
+ model.layers.38.mlp.down_proj: 5
303
+ model.layers.39.self_attn.q_proj: 7
304
+ model.layers.39.self_attn.k_proj: 6
305
+ model.layers.39.self_attn.v_proj: 8
306
+ model.layers.39.self_attn.o_proj: 7
307
+ model.layers.39.mlp.gate_proj: 8
308
+ model.layers.39.mlp.up_proj: 8
309
+ model.layers.39.mlp.down_proj: 7
310
+ model.layers.40.self_attn.q_proj: 6
311
+ model.layers.40.self_attn.k_proj: 8
312
+ model.layers.40.self_attn.v_proj: 8
313
+ model.layers.40.self_attn.o_proj: 7
314
+ model.layers.40.mlp.gate_proj: 6
315
+ model.layers.40.mlp.up_proj: 8
316
+ model.layers.40.mlp.down_proj: 8
317
+ model.layers.41.self_attn.q_proj: 8
318
+ model.layers.41.self_attn.k_proj: 7
319
+ model.layers.41.self_attn.v_proj: 8
320
+ model.layers.41.self_attn.o_proj: 7
321
+ model.layers.41.mlp.gate_proj: 5
322
+ model.layers.41.mlp.up_proj: 7
323
+ model.layers.41.mlp.down_proj: 6
324
+ model.layers.42.self_attn.q_proj: 6
325
+ model.layers.42.self_attn.k_proj: 6
326
+ model.layers.42.self_attn.v_proj: 7
327
+ model.layers.42.self_attn.o_proj: 7
328
+ model.layers.42.mlp.gate_proj: 7
329
+ model.layers.42.mlp.up_proj: 7
330
+ model.layers.42.mlp.down_proj: 8
331
+ model.layers.43.self_attn.q_proj: 5
332
+ model.layers.43.self_attn.k_proj: 7
333
+ model.layers.43.self_attn.v_proj: 6
334
+ model.layers.43.self_attn.o_proj: 7
335
+ model.layers.43.mlp.gate_proj: 7
336
+ model.layers.43.mlp.up_proj: 7
337
+ model.layers.43.mlp.down_proj: 7
338
+ model.layers.44.self_attn.q_proj: 8
339
+ model.layers.44.self_attn.k_proj: 8
340
+ model.layers.44.self_attn.v_proj: 8
341
+ model.layers.44.self_attn.o_proj: 6
342
+ model.layers.44.mlp.gate_proj: 7
343
+ model.layers.44.mlp.up_proj: 8
344
+ model.layers.44.mlp.down_proj: 7
345
+ model.layers.45.self_attn.q_proj: 7
346
+ model.layers.45.self_attn.k_proj: 8
347
+ model.layers.45.self_attn.v_proj: 8
348
+ model.layers.45.self_attn.o_proj: 8
349
+ model.layers.45.mlp.gate_proj: 5
350
+ model.layers.45.mlp.up_proj: 7
351
+ model.layers.45.mlp.down_proj: 5
352
+ model.layers.46.self_attn.q_proj: 7
353
+ model.layers.46.self_attn.k_proj: 6
354
+ model.layers.46.self_attn.v_proj: 8
355
+ model.layers.46.self_attn.o_proj: 8
356
+ model.layers.46.mlp.gate_proj: 8
357
+ model.layers.46.mlp.up_proj: 6
358
+ model.layers.46.mlp.down_proj: 8
359
+ model.layers.47.self_attn.q_proj: 7
360
+ model.layers.47.self_attn.k_proj: 6
361
+ model.layers.47.self_attn.v_proj: 7
362
+ model.layers.47.self_attn.o_proj: 5
363
+ model.layers.47.mlp.gate_proj: 7
364
+ model.layers.47.mlp.up_proj: 5
365
+ model.layers.47.mlp.down_proj: 5
366
+ model.layers.48.self_attn.q_proj: 8
367
+ model.layers.48.self_attn.k_proj: 8
368
+ model.layers.48.self_attn.v_proj: 8
369
+ model.layers.48.self_attn.o_proj: 8
370
+ model.layers.48.mlp.gate_proj: 7
371
+ model.layers.48.mlp.up_proj: 8
372
+ model.layers.48.mlp.down_proj: 7
373
+ model.layers.49.self_attn.q_proj: 4
374
+ model.layers.49.self_attn.k_proj: 8
375
+ model.layers.49.self_attn.v_proj: 6
376
+ model.layers.49.self_attn.o_proj: 5
377
+ model.layers.49.mlp.gate_proj: 6
378
+ model.layers.49.mlp.up_proj: 7
379
+ model.layers.49.mlp.down_proj: 6
380
+ model.layers.50.self_attn.q_proj: 7
381
+ model.layers.50.self_attn.k_proj: 7
382
+ model.layers.50.self_attn.v_proj: 5
383
+ model.layers.50.self_attn.o_proj: 7
384
+ model.layers.50.mlp.gate_proj: 5
385
+ model.layers.50.mlp.up_proj: 6
386
+ model.layers.50.mlp.down_proj: 7
387
+ model.layers.51.self_attn.q_proj: 5
388
+ model.layers.51.self_attn.k_proj: 6
389
+ model.layers.51.self_attn.v_proj: 5
390
+ model.layers.51.self_attn.o_proj: 7
391
+ model.layers.51.mlp.gate_proj: 5
392
+ model.layers.51.mlp.up_proj: 5
393
+ model.layers.51.mlp.down_proj: 7
394
+ model.layers.52.self_attn.q_proj: 5
395
+ model.layers.52.self_attn.k_proj: 8
396
+ model.layers.52.self_attn.v_proj: 8
397
+ model.layers.52.self_attn.o_proj: 7
398
+ model.layers.52.mlp.gate_proj: 6
399
+ model.layers.52.mlp.up_proj: 6
400
+ model.layers.52.mlp.down_proj: 5
401
+ model.layers.53.self_attn.q_proj: 8
402
+ model.layers.53.self_attn.k_proj: 7
403
+ model.layers.53.self_attn.v_proj: 7
404
+ model.layers.53.self_attn.o_proj: 5
405
+ model.layers.53.mlp.gate_proj: 6
406
+ model.layers.53.mlp.up_proj: 5
407
+ model.layers.53.mlp.down_proj: 5
408
+ model.layers.54.self_attn.q_proj: 5
409
+ model.layers.54.self_attn.k_proj: 7
410
+ model.layers.54.self_attn.v_proj: 7
411
+ model.layers.54.self_attn.o_proj: 8
412
+ model.layers.54.mlp.gate_proj: 6
413
+ model.layers.54.mlp.up_proj: 8
414
+ model.layers.54.mlp.down_proj: 5
415
+ model.layers.55.self_attn.q_proj: 6
416
+ model.layers.55.self_attn.k_proj: 5
417
+ model.layers.55.self_attn.v_proj: 8
418
+ model.layers.55.self_attn.o_proj: 6
419
+ model.layers.55.mlp.gate_proj: 7
420
+ model.layers.55.mlp.up_proj: 8
421
+ model.layers.55.mlp.down_proj: 6
422
+ model.layers.56.self_attn.q_proj: 8
423
+ model.layers.56.self_attn.k_proj: 4
424
+ model.layers.56.self_attn.v_proj: 5
425
+ model.layers.56.self_attn.o_proj: 7
426
+ model.layers.56.mlp.gate_proj: 6
427
+ model.layers.56.mlp.up_proj: 6
428
+ model.layers.56.mlp.down_proj: 6
429
+ model.layers.57.self_attn.q_proj: 5
430
+ model.layers.57.self_attn.k_proj: 5
431
+ model.layers.57.self_attn.v_proj: 5
432
+ model.layers.57.self_attn.o_proj: 7
433
+ model.layers.57.mlp.gate_proj: 6
434
+ model.layers.57.mlp.up_proj: 5
435
+ model.layers.57.mlp.down_proj: 6
436
+ model.layers.58.self_attn.q_proj: 5
437
+ model.layers.58.self_attn.k_proj: 5
438
+ model.layers.58.self_attn.v_proj: 7
439
+ model.layers.58.self_attn.o_proj: 5
440
+ model.layers.58.mlp.gate_proj: 5
441
+ model.layers.58.mlp.up_proj: 5
442
+ model.layers.58.mlp.down_proj: 6
443
+ model.layers.59.self_attn.q_proj: 5
444
+ model.layers.59.self_attn.k_proj: 8
445
+ model.layers.59.self_attn.v_proj: 8
446
+ model.layers.59.self_attn.o_proj: 5
447
+ model.layers.59.mlp.gate_proj: 6
448
+ model.layers.59.mlp.up_proj: 5
449
+ model.layers.59.mlp.down_proj: 7
450
+ model.layers.60.self_attn.q_proj: 7
451
+ model.layers.60.self_attn.k_proj: 7
452
+ model.layers.60.self_attn.v_proj: 7
453
+ model.layers.60.self_attn.o_proj: 7
454
+ model.layers.60.mlp.gate_proj: 6
455
+ model.layers.60.mlp.up_proj: 7
456
+ model.layers.60.mlp.down_proj: 5
457
+ model.layers.61.self_attn.q_proj: 7
458
+ model.layers.61.self_attn.k_proj: 7
459
+ model.layers.61.self_attn.v_proj: 8
460
+ model.layers.61.self_attn.o_proj: 7
461
+ model.layers.61.mlp.gate_proj: 7
462
+ model.layers.61.mlp.up_proj: 7
463
+ model.layers.61.mlp.down_proj: 5
464
+ model.layers.62.self_attn.q_proj: 7
465
+ model.layers.62.self_attn.k_proj: 8
466
+ model.layers.62.self_attn.v_proj: 8
467
+ model.layers.62.self_attn.o_proj: 8
468
+ model.layers.62.mlp.gate_proj: 5
469
+ model.layers.62.mlp.up_proj: 6
470
+ model.layers.62.mlp.down_proj: 7
471
+ model.layers.63.self_attn.q_proj: 7
472
+ model.layers.63.self_attn.k_proj: 8
473
+ model.layers.63.self_attn.v_proj: 6
474
+ model.layers.63.self_attn.o_proj: 7
475
+ model.layers.63.mlp.gate_proj: 8
476
+ model.layers.63.mlp.up_proj: 8
477
+ model.layers.63.mlp.down_proj: 5
478
+ model.layers.64.self_attn.q_proj: 8
479
+ model.layers.64.self_attn.k_proj: 6
480
+ model.layers.64.self_attn.v_proj: 7
481
+ model.layers.64.self_attn.o_proj: 7
482
+ model.layers.64.mlp.gate_proj: 6
483
+ model.layers.64.mlp.up_proj: 7
484
+ model.layers.64.mlp.down_proj: 7
485
+ model.layers.65.self_attn.q_proj: 8
486
+ model.layers.65.self_attn.k_proj: 8
487
+ model.layers.65.self_attn.v_proj: 7
488
+ model.layers.65.self_attn.o_proj: 8
489
+ model.layers.65.mlp.gate_proj: 7
490
+ model.layers.65.mlp.up_proj: 7
491
+ model.layers.65.mlp.down_proj: 8
492
+ model.layers.66.self_attn.q_proj: 8
493
+ model.layers.66.self_attn.k_proj: 8
494
+ model.layers.66.self_attn.v_proj: 8
495
+ model.layers.66.self_attn.o_proj: 8
496
+ model.layers.66.mlp.gate_proj: 8
497
+ model.layers.66.mlp.up_proj: 8
498
+ model.layers.66.mlp.down_proj: 8
499
+ model.layers.67.self_attn.q_proj: 8
500
+ model.layers.67.self_attn.k_proj: 8
501
+ model.layers.67.self_attn.v_proj: 7
502
+ model.layers.67.self_attn.o_proj: 7
503
+ model.layers.67.mlp.gate_proj: 7
504
+ model.layers.67.mlp.up_proj: 7
505
+ model.layers.67.mlp.down_proj: 6
506
+ model.layers.68.self_attn.q_proj: 7
507
+ model.layers.68.self_attn.k_proj: 5
508
+ model.layers.68.self_attn.v_proj: 7
509
+ model.layers.68.self_attn.o_proj: 5
510
+ model.layers.68.mlp.gate_proj: 7
511
+ model.layers.68.mlp.up_proj: 8
512
+ model.layers.68.mlp.down_proj: 6
513
+ model.layers.69.self_attn.q_proj: 7
514
+ model.layers.69.self_attn.k_proj: 8
515
+ model.layers.69.self_attn.v_proj: 8
516
+ model.layers.69.self_attn.o_proj: 7
517
+ model.layers.69.mlp.gate_proj: 6
518
+ model.layers.69.mlp.up_proj: 7
519
+ model.layers.69.mlp.down_proj: 6
520
+ model.layers.70.self_attn.q_proj: 7
521
+ model.layers.70.self_attn.k_proj: 8
522
+ model.layers.70.self_attn.v_proj: 7
523
+ model.layers.70.self_attn.o_proj: 4
524
+ model.layers.70.mlp.gate_proj: 7
525
+ model.layers.70.mlp.up_proj: 8
526
+ model.layers.70.mlp.down_proj: 6
527
+ model.layers.71.self_attn.q_proj: 5
528
+ model.layers.71.self_attn.k_proj: 8
529
+ model.layers.71.self_attn.v_proj: 6
530
+ model.layers.71.self_attn.o_proj: 8
531
+ model.layers.71.mlp.gate_proj: 7
532
+ model.layers.71.mlp.up_proj: 6
533
+ model.layers.71.mlp.down_proj: 5
534
+ model.layers.72.self_attn.q_proj: 7
535
+ model.layers.72.self_attn.k_proj: 6
536
+ model.layers.72.self_attn.v_proj: 5
537
+ model.layers.72.self_attn.o_proj: 7
538
+ model.layers.72.mlp.gate_proj: 8
539
+ model.layers.72.mlp.up_proj: 6
540
+ model.layers.72.mlp.down_proj: 7
541
+ model.layers.73.self_attn.q_proj: 7
542
+ model.layers.73.self_attn.k_proj: 7
543
+ model.layers.73.self_attn.v_proj: 8
544
+ model.layers.73.self_attn.o_proj: 7
545
+ model.layers.73.mlp.gate_proj: 6
546
+ model.layers.73.mlp.up_proj: 6
547
+ model.layers.73.mlp.down_proj: 7
548
+ model.layers.74.self_attn.q_proj: 7
549
+ model.layers.74.self_attn.k_proj: 6
550
+ model.layers.74.self_attn.v_proj: 8
551
+ model.layers.74.self_attn.o_proj: 7
552
+ model.layers.74.mlp.gate_proj: 8
553
+ model.layers.74.mlp.up_proj: 6
554
+ model.layers.74.mlp.down_proj: 7
555
+ model.layers.75.self_attn.q_proj: 7
556
+ model.layers.75.self_attn.k_proj: 6
557
+ model.layers.75.self_attn.v_proj: 5
558
+ model.layers.75.self_attn.o_proj: 5
559
+ model.layers.75.mlp.gate_proj: 8
560
+ model.layers.75.mlp.up_proj: 8
561
+ model.layers.75.mlp.down_proj: 6
562
+ model.layers.76.self_attn.q_proj: 6
563
+ model.layers.76.self_attn.k_proj: 8
564
+ model.layers.76.self_attn.v_proj: 8
565
+ model.layers.76.self_attn.o_proj: 7
566
+ model.layers.76.mlp.gate_proj: 7
567
+ model.layers.76.mlp.up_proj: 8
568
+ model.layers.76.mlp.down_proj: 6
569
+ model.layers.77.self_attn.q_proj: 8
570
+ model.layers.77.self_attn.k_proj: 8
571
+ model.layers.77.self_attn.v_proj: 6
572
+ model.layers.77.self_attn.o_proj: 8
573
+ model.layers.77.mlp.gate_proj: 6
574
+ model.layers.77.mlp.up_proj: 7
575
+ model.layers.77.mlp.down_proj: 7
576
+ model.layers.78.self_attn.q_proj: 7
577
+ model.layers.78.self_attn.k_proj: 8
578
+ model.layers.78.self_attn.v_proj: 5
579
+ model.layers.78.self_attn.o_proj: 8
580
+ model.layers.78.mlp.gate_proj: 6
581
+ model.layers.78.mlp.up_proj: 7
582
+ model.layers.78.mlp.down_proj: 7
583
+ model.layers.79.self_attn.q_proj: 7
584
+ model.layers.79.self_attn.k_proj: 7
585
+ model.layers.79.self_attn.v_proj: 6
586
+ model.layers.79.self_attn.o_proj: 8
587
+ model.layers.79.mlp.gate_proj: 8
588
+ model.layers.79.mlp.up_proj: 8
589
+ model.layers.79.mlp.down_proj: 7
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|finetune_right_pad_id|>"
17
+ }
humming/Llama-3.3-70B-Instruct/Llama-3.3-70B-Instruct/ll_bsearch_kl0.01_eap0.985_sha_bw6.55_4-5-6-7-8bit_seed42/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|finetune_right_pad_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/README.md ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Quantized Model Checkpoint
2
+
3
+ **Base model:** Qwen/Qwen3-32B
4
+
5
+ **Average bitwidth:** 4.9762
6
+
7
+ **Sensitivity method:** shapley
8
+
9
+ **Constraints:**
10
+ - max_kl: 0.005
11
+ - min_eap: 0.99
12
+
13
+ **Metrics:**
14
+ - final_kl: 0.001967
15
+ - final_eap: 0.990037
16
+ - final_etl: 0.009963
17
+
18
+ See `quantization_config.txt` for full configuration details.
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 25600,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention"
80
+ ],
81
+ "max_position_embeddings": 40960,
82
+ "max_window_layers": 64,
83
+ "model_type": "qwen3",
84
+ "num_attention_heads": 64,
85
+ "num_hidden_layers": 64,
86
+ "num_key_value_heads": 8,
87
+ "rms_norm_eps": 1e-06,
88
+ "rope_scaling": null,
89
+ "rope_theta": 1000000,
90
+ "sliding_window": null,
91
+ "tie_word_embeddings": false,
92
+ "transformers_version": "4.57.3",
93
+ "use_cache": false,
94
+ "use_sliding_window": false,
95
+ "vocab_size": 151936
96
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/humming_online_quant_config.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quant_method": "gptq",
3
+ "bits": 5,
4
+ "group_size": 128,
5
+ "dynamic": {
6
+ "+:model\\.layers\\.0\\.mlp\\.down_proj": {
7
+ "bits": 4
8
+ },
9
+ "+:model\\.layers\\.2\\.self_attn\\.k_proj": {
10
+ "bits": 8
11
+ },
12
+ "+:model\\.layers\\.0\\.self_attn\\.k_proj": {
13
+ "bits": 8
14
+ },
15
+ "+:model\\.layers\\.0\\.self_attn\\.v_proj": {
16
+ "bits": 8
17
+ },
18
+ "+:model\\.layers\\.2\\.mlp\\.gate_proj": {
19
+ "bits": 4
20
+ },
21
+ "+:model\\.layers\\.1\\.mlp\\.down_proj": {
22
+ "bits": 4
23
+ },
24
+ "+:model\\.layers\\.0\\.mlp\\.up_proj": {
25
+ "bits": 4
26
+ },
27
+ "+:model\\.layers\\.1\\.self_attn\\.v_proj": {
28
+ "bits": 7
29
+ },
30
+ "+:model\\.layers\\.2\\.mlp\\.up_proj": {
31
+ "bits": 4
32
+ },
33
+ "+:model\\.layers\\.0\\.mlp\\.gate_proj": {
34
+ "bits": 4
35
+ },
36
+ "+:model\\.layers\\.1\\.self_attn\\.k_proj": {
37
+ "bits": 7
38
+ },
39
+ "+:model\\.layers\\.2\\.self_attn\\.v_proj": {
40
+ "bits": 8
41
+ },
42
+ "+:model\\.layers\\.1\\.mlp\\.up_proj": {
43
+ "bits": 4
44
+ },
45
+ "+:model\\.layers\\.1\\.self_attn\\.o_proj": {
46
+ "bits": 4
47
+ },
48
+ "+:model\\.layers\\.1\\.mlp\\.gate_proj": {
49
+ "bits": 4
50
+ },
51
+ "+:model\\.layers\\.7\\.self_attn\\.v_proj": {
52
+ "bits": 8
53
+ },
54
+ "+:model\\.layers\\.6\\.mlp\\.gate_proj": {
55
+ "bits": 4
56
+ },
57
+ "+:model\\.layers\\.9\\.self_attn\\.k_proj": {
58
+ "bits": 7
59
+ },
60
+ "+:model\\.layers\\.21\\.mlp\\.gate_proj": {
61
+ "bits": 4
62
+ },
63
+ "+:model\\.layers\\.38\\.self_attn\\.k_proj": {
64
+ "bits": 8
65
+ },
66
+ "+:model\\.layers\\.32\\.self_attn\\.k_proj": {
67
+ "bits": 7
68
+ },
69
+ "+:model\\.layers\\.19\\.self_attn\\.q_proj": {
70
+ "bits": 4
71
+ },
72
+ "+:model\\.layers\\.33\\.self_attn\\.k_proj": {
73
+ "bits": 8
74
+ },
75
+ "+:model\\.layers\\.15\\.self_attn\\.k_proj": {
76
+ "bits": 8
77
+ },
78
+ "+:model\\.layers\\.21\\.mlp\\.down_proj": {
79
+ "bits": 4
80
+ },
81
+ "+:model\\.layers\\.3\\.mlp\\.up_proj": {
82
+ "bits": 4
83
+ },
84
+ "+:model\\.layers\\.2\\.mlp\\.down_proj": {
85
+ "bits": 4
86
+ },
87
+ "+:model\\.layers\\.3\\.mlp\\.down_proj": {
88
+ "bits": 4
89
+ },
90
+ "+:model\\.layers\\.8\\.self_attn\\.q_proj": {
91
+ "bits": 7
92
+ },
93
+ "+:model\\.layers\\.5\\.mlp\\.gate_proj": {
94
+ "bits": 4
95
+ },
96
+ "+:model\\.layers\\.9\\.self_attn\\.q_proj": {
97
+ "bits": 6
98
+ },
99
+ "+:model\\.layers\\.7\\.mlp\\.down_proj": {
100
+ "bits": 4
101
+ },
102
+ "+:model\\.layers\\.8\\.mlp\\.gate_proj": {
103
+ "bits": 4
104
+ },
105
+ "+:model\\.layers\\.3\\.self_attn\\.v_proj": {
106
+ "bits": 7
107
+ },
108
+ "+:model\\.layers\\.6\\.mlp\\.down_proj": {
109
+ "bits": 8
110
+ },
111
+ "+:model\\.layers\\.16\\.mlp\\.down_proj": {
112
+ "bits": 4
113
+ },
114
+ "+:model\\.layers\\.22\\.self_attn\\.o_proj": {
115
+ "bits": 6
116
+ },
117
+ "+:model\\.layers\\.38\\.mlp\\.down_proj": {
118
+ "bits": 6
119
+ },
120
+ "+:model\\.layers\\.3\\.mlp\\.gate_proj": {
121
+ "bits": 4
122
+ },
123
+ "+:model\\.layers\\.10\\.self_attn\\.q_proj": {
124
+ "bits": 6
125
+ },
126
+ "+:model\\.layers\\.14\\.self_attn\\.k_proj": {
127
+ "bits": 8
128
+ },
129
+ "+:model\\.layers\\.16\\.self_attn\\.o_proj": {
130
+ "bits": 4
131
+ },
132
+ "+:model\\.layers\\.20\\.mlp\\.up_proj": {
133
+ "bits": 4
134
+ },
135
+ "+:model\\.layers\\.26\\.self_attn\\.q_proj": {
136
+ "bits": 6
137
+ },
138
+ "+:model\\.layers\\.9\\.mlp\\.up_proj": {
139
+ "bits": 4
140
+ },
141
+ "+:model\\.layers\\.3\\.self_attn\\.k_proj": {
142
+ "bits": 7
143
+ },
144
+ "+:model\\.layers\\.4\\.mlp\\.gate_proj": {
145
+ "bits": 4
146
+ },
147
+ "+:model\\.layers\\.5\\.mlp\\.up_proj": {
148
+ "bits": 4
149
+ },
150
+ "+:model\\.layers\\.8\\.self_attn\\.k_proj": {
151
+ "bits": 7
152
+ },
153
+ "+:model\\.layers\\.30\\.self_attn\\.v_proj": {
154
+ "bits": 7
155
+ },
156
+ "+:model\\.layers\\.3\\.self_attn\\.q_proj": {
157
+ "bits": 6
158
+ },
159
+ "+:model\\.layers\\.10\\.self_attn\\.v_proj": {
160
+ "bits": 7
161
+ },
162
+ "+:model\\.layers\\.10\\.mlp\\.up_proj": {
163
+ "bits": 4
164
+ },
165
+ "+:model\\.layers\\.6\\.self_attn\\.v_proj": {
166
+ "bits": 8
167
+ },
168
+ "+:model\\.layers\\.6\\.self_attn\\.o_proj": {
169
+ "bits": 4
170
+ },
171
+ "+:model\\.layers\\.8\\.self_attn\\.o_proj": {
172
+ "bits": 6
173
+ },
174
+ "+:model\\.layers\\.8\\.self_attn\\.v_proj": {
175
+ "bits": 7
176
+ },
177
+ "+:model\\.layers\\.10\\.mlp\\.gate_proj": {
178
+ "bits": 4
179
+ },
180
+ "+:model\\.layers\\.10\\.self_attn\\.k_proj": {
181
+ "bits": 7
182
+ },
183
+ "+:model\\.layers\\.5\\.self_attn\\.v_proj": {
184
+ "bits": 8
185
+ },
186
+ "+:model\\.layers\\.4\\.self_attn\\.o_proj": {
187
+ "bits": 6
188
+ },
189
+ "+:model\\.layers\\.4\\.mlp\\.down_proj": {
190
+ "bits": 4
191
+ },
192
+ "+:model\\.layers\\.5\\.mlp\\.down_proj": {
193
+ "bits": 4
194
+ },
195
+ "+:model\\.layers\\.7\\.self_attn\\.k_proj": {
196
+ "bits": 8
197
+ },
198
+ "+:model\\.layers\\.5\\.self_attn\\.k_proj": {
199
+ "bits": 8
200
+ },
201
+ "+:model\\.layers\\.6\\.mlp\\.up_proj": {
202
+ "bits": 4
203
+ },
204
+ "+:model\\.layers\\.9\\.self_attn\\.v_proj": {
205
+ "bits": 7
206
+ },
207
+ "+:model\\.layers\\.9\\.mlp\\.down_proj": {
208
+ "bits": 4
209
+ },
210
+ "+:model\\.layers\\.4\\.mlp\\.up_proj": {
211
+ "bits": 4
212
+ },
213
+ "+:model\\.layers\\.9\\.mlp\\.gate_proj": {
214
+ "bits": 4
215
+ },
216
+ "+:model\\.layers\\.6\\.self_attn\\.k_proj": {
217
+ "bits": 8
218
+ },
219
+ "+:model\\.layers\\.8\\.mlp\\.up_proj": {
220
+ "bits": 4
221
+ },
222
+ "+:model\\.layers\\.20\\.self_attn\\.v_proj": {
223
+ "bits": 8
224
+ },
225
+ "+:model\\.layers\\.13\\.self_attn\\.v_proj": {
226
+ "bits": 8
227
+ },
228
+ "+:model\\.layers\\.27\\.self_attn\\.k_proj": {
229
+ "bits": 7
230
+ },
231
+ "+:model\\.layers\\.20\\.mlp\\.gate_proj": {
232
+ "bits": 4
233
+ },
234
+ "+:model\\.layers\\.35\\.self_attn\\.q_proj": {
235
+ "bits": 7
236
+ },
237
+ "+:model\\.layers\\.15\\.self_attn\\.v_proj": {
238
+ "bits": 8
239
+ },
240
+ "+:model\\.layers\\.29\\.mlp\\.gate_proj": {
241
+ "bits": 6
242
+ },
243
+ "+:model\\.layers\\.17\\.mlp\\.up_proj": {
244
+ "bits": 4
245
+ },
246
+ "+:model\\.layers\\.28\\.self_attn\\.v_proj": {
247
+ "bits": 7
248
+ },
249
+ "+:model\\.layers\\.38\\.mlp\\.up_proj": {
250
+ "bits": 6
251
+ },
252
+ "+:model\\.layers\\.39\\.self_attn\\.q_proj": {
253
+ "bits": 6
254
+ },
255
+ "+:model\\.layers\\.11\\.self_attn\\.v_proj": {
256
+ "bits": 7
257
+ },
258
+ "+:model\\.layers\\.12\\.self_attn\\.k_proj": {
259
+ "bits": 7
260
+ },
261
+ "+:model\\.layers\\.16\\.mlp\\.up_proj": {
262
+ "bits": 4
263
+ },
264
+ "+:model\\.layers\\.18\\.self_attn\\.o_proj": {
265
+ "bits": 6
266
+ },
267
+ "+:model\\.layers\\.20\\.self_attn\\.o_proj": {
268
+ "bits": 4
269
+ },
270
+ "+:model\\.layers\\.29\\.self_attn\\.k_proj": {
271
+ "bits": 8
272
+ },
273
+ "+:model\\.layers\\.38\\.self_attn\\.o_proj": {
274
+ "bits": 4
275
+ },
276
+ "+:model\\.layers\\.14\\.mlp\\.down_proj": {
277
+ "bits": 4
278
+ },
279
+ "+:model\\.layers\\.33\\.mlp\\.gate_proj": {
280
+ "bits": 6
281
+ },
282
+ "+:model\\.layers\\.16\\.self_attn\\.k_proj": {
283
+ "bits": 7
284
+ },
285
+ "+:model\\.layers\\.16\\.self_attn\\.v_proj": {
286
+ "bits": 7
287
+ },
288
+ "+:model\\.layers\\.25\\.self_attn\\.o_proj": {
289
+ "bits": 4
290
+ },
291
+ "+:model\\.layers\\.18\\.self_attn\\.k_proj": {
292
+ "bits": 8
293
+ },
294
+ "+:model\\.layers\\.16\\.mlp\\.gate_proj": {
295
+ "bits": 4
296
+ },
297
+ "+:model\\.layers\\.19\\.mlp\\.up_proj": {
298
+ "bits": 4
299
+ },
300
+ "+:model\\.layers\\.26\\.self_attn\\.k_proj": {
301
+ "bits": 6
302
+ },
303
+ "+:model\\.layers\\.11\\.mlp\\.down_proj": {
304
+ "bits": 4
305
+ },
306
+ "+:model\\.layers\\.12\\.mlp\\.up_proj": {
307
+ "bits": 4
308
+ },
309
+ "+:model\\.layers\\.17\\.self_attn\\.o_proj": {
310
+ "bits": 4
311
+ },
312
+ "+:model\\.layers\\.27\\.self_attn\\.v_proj": {
313
+ "bits": 7
314
+ },
315
+ "+:model\\.layers\\.34\\.self_attn\\.k_proj": {
316
+ "bits": 6
317
+ },
318
+ "+:model\\.layers\\.37\\.self_attn\\.q_proj": {
319
+ "bits": 6
320
+ },
321
+ "+:model\\.layers\\.14\\.self_attn\\.v_proj": {
322
+ "bits": 8
323
+ },
324
+ "+:model\\.layers\\.17\\.self_attn\\.v_proj": {
325
+ "bits": 8
326
+ },
327
+ "+:model\\.layers\\.24\\.self_attn\\.v_proj": {
328
+ "bits": 8
329
+ },
330
+ "+:model\\.layers\\.25\\.self_attn\\.k_proj": {
331
+ "bits": 8
332
+ },
333
+ "+:model\\.layers\\.31\\.self_attn\\.v_proj": {
334
+ "bits": 7
335
+ },
336
+ "+:model\\.layers\\.33\\.mlp\\.up_proj": {
337
+ "bits": 6
338
+ },
339
+ "+:model\\.layers\\.39\\.self_attn\\.o_proj": {
340
+ "bits": 6
341
+ },
342
+ "+:model\\.layers\\.11\\.mlp\\.up_proj": {
343
+ "bits": 4
344
+ },
345
+ "+:model\\.layers\\.12\\.mlp\\.gate_proj": {
346
+ "bits": 4
347
+ },
348
+ "+:model\\.layers\\.17\\.mlp\\.gate_proj": {
349
+ "bits": 4
350
+ },
351
+ "+:model\\.layers\\.20\\.mlp\\.down_proj": {
352
+ "bits": 4
353
+ },
354
+ "+:model\\.layers\\.32\\.mlp\\.down_proj": {
355
+ "bits": 4
356
+ },
357
+ "+:model\\.layers\\.39\\.self_attn\\.k_proj": {
358
+ "bits": 8
359
+ },
360
+ "+:model\\.layers\\.13\\.self_attn\\.k_proj": {
361
+ "bits": 8
362
+ },
363
+ "+:model\\.layers\\.14\\.self_attn\\.q_proj": {
364
+ "bits": 4
365
+ },
366
+ "+:model\\.layers\\.14\\.mlp\\.up_proj": {
367
+ "bits": 4
368
+ },
369
+ "+:model\\.layers\\.19\\.self_attn\\.k_proj": {
370
+ "bits": 7
371
+ },
372
+ "+:model\\.layers\\.37\\.self_attn\\.v_proj": {
373
+ "bits": 8
374
+ },
375
+ "+:model\\.layers\\.11\\.self_attn\\.k_proj": {
376
+ "bits": 7
377
+ },
378
+ "+:model\\.layers\\.18\\.self_attn\\.q_proj": {
379
+ "bits": 4
380
+ },
381
+ "+:model\\.layers\\.27\\.self_attn\\.q_proj": {
382
+ "bits": 6
383
+ },
384
+ "+:model\\.layers\\.38\\.self_attn\\.v_proj": {
385
+ "bits": 8
386
+ },
387
+ "+:model\\.layers\\.10\\.mlp\\.down_proj": {
388
+ "bits": 4
389
+ },
390
+ "+:model\\.layers\\.12\\.self_attn\\.v_proj": {
391
+ "bits": 7
392
+ },
393
+ "+:model\\.layers\\.13\\.mlp\\.gate_proj": {
394
+ "bits": 4
395
+ },
396
+ "+:model\\.layers\\.14\\.mlp\\.gate_proj": {
397
+ "bits": 4
398
+ },
399
+ "+:model\\.layers\\.15\\.mlp\\.down_proj": {
400
+ "bits": 4
401
+ },
402
+ "+:model\\.layers\\.22\\.self_attn\\.v_proj": {
403
+ "bits": 7
404
+ },
405
+ "+:model\\.layers\\.23\\.self_attn\\.k_proj": {
406
+ "bits": 8
407
+ },
408
+ "+:model\\.layers\\.11\\.mlp\\.gate_proj": {
409
+ "bits": 4
410
+ },
411
+ "+:model\\.layers\\.32\\.self_attn\\.q_proj": {
412
+ "bits": 7
413
+ },
414
+ "+:model\\.layers\\.37\\.self_attn\\.k_proj": {
415
+ "bits": 8
416
+ },
417
+ "+:model\\.layers\\.37\\.mlp\\.up_proj": {
418
+ "bits": 6
419
+ },
420
+ "+:model\\.layers\\.11\\.self_attn\\.o_proj": {
421
+ "bits": 4
422
+ },
423
+ "+:model\\.layers\\.13\\.self_attn\\.o_proj": {
424
+ "bits": 6
425
+ },
426
+ "+:model\\.layers\\.13\\.mlp\\.up_proj": {
427
+ "bits": 4
428
+ },
429
+ "+:model\\.layers\\.17\\.self_attn\\.k_proj": {
430
+ "bits": 8
431
+ },
432
+ "+:model\\.layers\\.18\\.self_attn\\.v_proj": {
433
+ "bits": 8
434
+ },
435
+ "+:model\\.layers\\.18\\.mlp\\.down_proj": {
436
+ "bits": 4
437
+ },
438
+ "+:model\\.layers\\.20\\.self_attn\\.k_proj": {
439
+ "bits": 8
440
+ },
441
+ "+:model\\.layers\\.28\\.self_attn\\.k_proj": {
442
+ "bits": 7
443
+ },
444
+ "+:model\\.layers\\.31\\.self_attn\\.k_proj": {
445
+ "bits": 7
446
+ },
447
+ "+:model\\.layers\\.31\\.mlp\\.down_proj": {
448
+ "bits": 4
449
+ },
450
+ "+:model\\.layers\\.32\\.self_attn\\.o_proj": {
451
+ "bits": 6
452
+ },
453
+ "+:model\\.layers\\.33\\.self_attn\\.v_proj": {
454
+ "bits": 8
455
+ },
456
+ "+:model\\.layers\\.25\\.mlp\\.down_proj": {
457
+ "bits": 4
458
+ },
459
+ "+:model\\.layers\\.32\\.mlp\\.up_proj": {
460
+ "bits": 6
461
+ },
462
+ "+:model\\.layers\\.28\\.self_attn\\.o_proj": {
463
+ "bits": 6
464
+ },
465
+ "+:model\\.layers\\.24\\.mlp\\.down_proj": {
466
+ "bits": 4
467
+ },
468
+ "+:model\\.layers\\.19\\.self_attn\\.v_proj": {
469
+ "bits": 7
470
+ },
471
+ "+:model\\.layers\\.19\\.mlp\\.gate_proj": {
472
+ "bits": 4
473
+ },
474
+ "+:model\\.layers\\.19\\.mlp\\.down_proj": {
475
+ "bits": 4
476
+ },
477
+ "+:model\\.layers\\.21\\.mlp\\.up_proj": {
478
+ "bits": 4
479
+ },
480
+ "+:model\\.layers\\.23\\.self_attn\\.v_proj": {
481
+ "bits": 8
482
+ },
483
+ "+:model\\.layers\\.24\\.self_attn\\.q_proj": {
484
+ "bits": 6
485
+ },
486
+ "+:model\\.layers\\.26\\.self_attn\\.o_proj": {
487
+ "bits": 6
488
+ },
489
+ "+:model\\.layers\\.31\\.self_attn\\.o_proj": {
490
+ "bits": 6
491
+ },
492
+ "+:model\\.layers\\.31\\.mlp\\.up_proj": {
493
+ "bits": 6
494
+ },
495
+ "+:model\\.layers\\.36\\.self_attn\\.v_proj": {
496
+ "bits": 8
497
+ },
498
+ "+:model\\.layers\\.22\\.self_attn\\.k_proj": {
499
+ "bits": 7
500
+ },
501
+ "+:model\\.layers\\.29\\.self_attn\\.v_proj": {
502
+ "bits": 8
503
+ },
504
+ "+:model\\.layers\\.32\\.self_attn\\.v_proj": {
505
+ "bits": 7
506
+ },
507
+ "+:model\\.layers\\.33\\.self_attn\\.o_proj": {
508
+ "bits": 6
509
+ },
510
+ "+:model\\.layers\\.34\\.mlp\\.gate_proj": {
511
+ "bits": 6
512
+ },
513
+ "+:model\\.layers\\.37\\.mlp\\.gate_proj": {
514
+ "bits": 6
515
+ },
516
+ "+:model\\.layers\\.39\\.self_attn\\.v_proj": {
517
+ "bits": 8
518
+ },
519
+ "+:model\\.layers\\.39\\.mlp\\.gate_proj": {
520
+ "bits": 6
521
+ },
522
+ "+:model\\.layers\\.24\\.self_attn\\.k_proj": {
523
+ "bits": 8
524
+ },
525
+ "+:model\\.layers\\.25\\.self_attn\\.v_proj": {
526
+ "bits": 8
527
+ },
528
+ "+:model\\.layers\\.29\\.mlp\\.up_proj": {
529
+ "bits": 6
530
+ },
531
+ "+:model\\.layers\\.30\\.self_attn\\.k_proj": {
532
+ "bits": 7
533
+ },
534
+ "+:model\\.layers\\.30\\.self_attn\\.o_proj": {
535
+ "bits": 6
536
+ },
537
+ "+:model\\.layers\\.26\\.self_attn\\.v_proj": {
538
+ "bits": 6
539
+ },
540
+ "+:model\\.layers\\.32\\.mlp\\.gate_proj": {
541
+ "bits": 6
542
+ },
543
+ "+:model\\.layers\\.35\\.self_attn\\.v_proj": {
544
+ "bits": 7
545
+ },
546
+ "+:model\\.layers\\.38\\.self_attn\\.q_proj": {
547
+ "bits": 7
548
+ },
549
+ "+:model\\.layers\\.38\\.mlp\\.gate_proj": {
550
+ "bits": 6
551
+ },
552
+ "+:model\\.layers\\.31\\.mlp\\.gate_proj": {
553
+ "bits": 6
554
+ },
555
+ "+:model\\.layers\\.33\\.mlp\\.down_proj": {
556
+ "bits": 4
557
+ },
558
+ "+:model\\.layers\\.36\\.self_attn\\.o_proj": {
559
+ "bits": 6
560
+ },
561
+ "+:model\\.layers\\.39\\.mlp\\.up_proj": {
562
+ "bits": 6
563
+ },
564
+ "+:model\\.layers\\.34\\.self_attn\\.q_proj": {
565
+ "bits": 6
566
+ },
567
+ "+:model\\.layers\\.34\\.self_attn\\.v_proj": {
568
+ "bits": 6
569
+ },
570
+ "+:model\\.layers\\.35\\.self_attn\\.k_proj": {
571
+ "bits": 7
572
+ },
573
+ "+:model\\.layers\\.36\\.self_attn\\.q_proj": {
574
+ "bits": 7
575
+ },
576
+ "+:model\\.layers\\.36\\.self_attn\\.k_proj": {
577
+ "bits": 8
578
+ }
579
+ }
580
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/model.safetensors.index.json ADDED
@@ -0,0 +1,715 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 32762123264,
4
+ "total_size": 65524246528
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00014-of-00014.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
46
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
57
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
68
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
79
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
90
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
101
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
112
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
123
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
134
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
145
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
156
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
167
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
178
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
189
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
200
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
211
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
222
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
233
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
244
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
255
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
266
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
277
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
288
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
299
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
300
+ "model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
303
+ "model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
304
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
305
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
310
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
311
+ "model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
314
+ "model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
315
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
316
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
322
+ "model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
325
+ "model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
326
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
327
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
332
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
336
+ "model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
337
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
338
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
339
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
340
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
341
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
342
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
343
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
344
+ "model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
345
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
346
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
347
+ "model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
348
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
349
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
350
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
351
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
352
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
353
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
354
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
355
+ "model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
356
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
357
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
358
+ "model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
359
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
360
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
361
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
362
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
363
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
364
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
365
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
366
+ "model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
367
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
368
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
369
+ "model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
370
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
371
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
372
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
373
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
374
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
375
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
376
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
377
+ "model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
378
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
379
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
380
+ "model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
381
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
382
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
383
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
384
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
385
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
386
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
387
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
388
+ "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
389
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
390
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
391
+ "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
392
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
393
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
394
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
395
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
396
+ "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
397
+ "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
398
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
399
+ "model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
400
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
401
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
402
+ "model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
403
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
404
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
405
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
406
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
407
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
408
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
409
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
410
+ "model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
411
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
412
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
413
+ "model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
414
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
415
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
417
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
418
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
419
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
420
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
421
+ "model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
422
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
423
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
424
+ "model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
425
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
426
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
427
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
428
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
429
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
430
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
431
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
432
+ "model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
433
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
434
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
435
+ "model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
436
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
437
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
438
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
439
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
440
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
441
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
442
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
443
+ "model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
444
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
445
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
446
+ "model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
447
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
448
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
449
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
450
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
451
+ "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
452
+ "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
453
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
454
+ "model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
455
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
456
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
457
+ "model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
458
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
459
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
460
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
461
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
462
+ "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
463
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
464
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
465
+ "model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
466
+ "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
467
+ "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
468
+ "model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
469
+ "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
470
+ "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
471
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
472
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
473
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
474
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
475
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
476
+ "model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
477
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
478
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
479
+ "model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
480
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
481
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
482
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
483
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
484
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
485
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
486
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
487
+ "model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
488
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
489
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
490
+ "model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
491
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
492
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
493
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
494
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
495
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
496
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
497
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
498
+ "model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
499
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
500
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
501
+ "model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
502
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
503
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
504
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
505
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
506
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
507
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
508
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
509
+ "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
510
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
511
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
512
+ "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
513
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
514
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
515
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
516
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
517
+ "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
518
+ "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
519
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
520
+ "model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
521
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
522
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
523
+ "model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
524
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
525
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
526
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
527
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
528
+ "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
529
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
530
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
531
+ "model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
532
+ "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
533
+ "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
534
+ "model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
535
+ "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
536
+ "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
537
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
538
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
539
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
540
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
541
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
542
+ "model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
543
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
544
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
545
+ "model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
546
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
547
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
549
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
550
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
551
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
552
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
553
+ "model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
554
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
555
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
556
+ "model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
557
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
558
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
559
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
560
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
561
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
562
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
563
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
564
+ "model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
565
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
566
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
567
+ "model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
568
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
569
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
570
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
571
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
572
+ "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
573
+ "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
574
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
575
+ "model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
576
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
577
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
578
+ "model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
579
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
580
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
581
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
582
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
583
+ "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
584
+ "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
585
+ "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
586
+ "model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
587
+ "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
588
+ "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
589
+ "model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
590
+ "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
591
+ "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
592
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
593
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
594
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
595
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
596
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
597
+ "model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
598
+ "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
599
+ "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
600
+ "model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
601
+ "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
602
+ "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
603
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
604
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
605
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
606
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
607
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
608
+ "model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
609
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
610
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
611
+ "model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
612
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
613
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
614
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
615
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
616
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
617
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
618
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
619
+ "model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
620
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
621
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
622
+ "model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
623
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
624
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
625
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
626
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
627
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
628
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
629
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
630
+ "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
631
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
632
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
633
+ "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
634
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
635
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
636
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
637
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
638
+ "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
639
+ "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
640
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
641
+ "model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
642
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
643
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
644
+ "model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
645
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
646
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
647
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
648
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
649
+ "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
650
+ "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
651
+ "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
652
+ "model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
653
+ "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
654
+ "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
655
+ "model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
656
+ "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
657
+ "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
658
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
659
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
660
+ "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
661
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
662
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
663
+ "model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
664
+ "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
665
+ "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
666
+ "model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
667
+ "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
668
+ "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
669
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
670
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
671
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
672
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
673
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
674
+ "model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
675
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
676
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
677
+ "model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
678
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
679
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
+ "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
686
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
+ "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
689
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
691
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
692
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
693
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
694
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
695
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
696
+ "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
697
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
698
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
699
+ "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
700
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
701
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
702
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
703
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
704
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
705
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
706
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
707
+ "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
708
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
709
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
710
+ "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
711
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
712
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
713
+ "model.norm.weight": "model-00014-of-00014.safetensors"
714
+ }
715
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/quantization_config.txt ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model: Qwen/Qwen3-32B
2
+ # Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4_5_6_7_8bit_asym_g128/Qwen3-32B/4bit
3
+ # Sensitivity method: shapley
4
+ # Estimation method: permutation
5
+ # Available bitwidths: [4, 5, 6, 7, 8]
6
+ # Bitwidth map: {4: 4.156, 5: 5.156, 6: 6.156, 7: 7.156, 8: 8.156}
7
+ #
8
+ # Mode: binary_search_constraint (measured)
9
+ # Constraint max_kl: 0.005
10
+ # Constraint min_eap: 0.99
11
+ # Weights: nll=0.0, kl=0.0, eap=1.0
12
+ #
13
+ # Average bitwidth: 4.9762
14
+ # Total params: 19503513600
15
+ # Total bits: 97052629402
16
+ # Final KL: 0.001967
17
+ # Final EAP: 0.990037
18
+ # Final ETL: 0.009963
19
+ # Satisfies constraints: True
20
+ # Solver calls: 9
21
+ # Evaluations: 9
22
+ #
23
+ # Bitwidth distribution:
24
+ # 8-bit: 41 layers (14.6%)
25
+ # 7-bit: 37 layers (13.2%)
26
+ # 6-bit: 42 layers (15.0%)
27
+ # 5-bit: 89 layers (31.8%)
28
+ # 4-bit: 71 layers (25.4%)
29
+ #
30
+ model.layers.0.mlp.down_proj: 4
31
+ model.layers.2.self_attn.k_proj: 8
32
+ model.layers.0.self_attn.k_proj: 8
33
+ model.layers.0.self_attn.v_proj: 8
34
+ model.layers.2.mlp.gate_proj: 4
35
+ model.layers.1.mlp.down_proj: 4
36
+ model.layers.0.mlp.up_proj: 4
37
+ model.layers.1.self_attn.v_proj: 7
38
+ model.layers.2.mlp.up_proj: 4
39
+ model.layers.0.mlp.gate_proj: 4
40
+ model.layers.1.self_attn.q_proj: 5
41
+ model.layers.0.self_attn.o_proj: 5
42
+ model.layers.1.self_attn.k_proj: 7
43
+ model.layers.2.self_attn.q_proj: 5
44
+ model.layers.2.self_attn.v_proj: 8
45
+ model.layers.2.self_attn.o_proj: 5
46
+ model.layers.0.self_attn.q_proj: 5
47
+ model.layers.1.mlp.up_proj: 4
48
+ model.layers.1.self_attn.o_proj: 4
49
+ model.layers.1.mlp.gate_proj: 4
50
+ model.layers.7.self_attn.v_proj: 8
51
+ model.layers.6.mlp.gate_proj: 4
52
+ model.layers.9.self_attn.k_proj: 7
53
+ model.layers.7.self_attn.q_proj: 5
54
+ model.layers.21.mlp.gate_proj: 4
55
+ model.layers.38.self_attn.k_proj: 8
56
+ model.layers.32.self_attn.k_proj: 7
57
+ model.layers.29.mlp.down_proj: 5
58
+ model.layers.19.self_attn.q_proj: 4
59
+ model.layers.33.self_attn.k_proj: 8
60
+ model.layers.15.self_attn.k_proj: 8
61
+ model.layers.21.mlp.down_proj: 4
62
+ model.layers.3.self_attn.o_proj: 5
63
+ model.layers.3.mlp.up_proj: 4
64
+ model.layers.2.mlp.down_proj: 4
65
+ model.layers.3.mlp.down_proj: 4
66
+ model.layers.8.self_attn.q_proj: 7
67
+ model.layers.24.mlp.up_proj: 5
68
+ model.layers.5.mlp.gate_proj: 4
69
+ model.layers.9.self_attn.q_proj: 6
70
+ model.layers.8.mlp.down_proj: 5
71
+ model.layers.7.mlp.down_proj: 4
72
+ model.layers.8.mlp.gate_proj: 4
73
+ model.layers.3.self_attn.v_proj: 7
74
+ model.layers.6.mlp.down_proj: 8
75
+ model.layers.13.mlp.down_proj: 5
76
+ model.layers.16.mlp.down_proj: 4
77
+ model.layers.22.self_attn.o_proj: 6
78
+ model.layers.38.mlp.down_proj: 6
79
+ model.layers.3.mlp.gate_proj: 4
80
+ model.layers.10.self_attn.q_proj: 6
81
+ model.layers.14.self_attn.k_proj: 8
82
+ model.layers.16.self_attn.o_proj: 4
83
+ model.layers.20.mlp.up_proj: 4
84
+ model.layers.26.self_attn.q_proj: 6
85
+ model.layers.4.self_attn.q_proj: 5
86
+ model.layers.9.mlp.up_proj: 4
87
+ model.layers.15.self_attn.o_proj: 5
88
+ model.layers.20.self_attn.q_proj: 5
89
+ model.layers.3.self_attn.k_proj: 7
90
+ model.layers.4.mlp.gate_proj: 4
91
+ model.layers.5.mlp.up_proj: 4
92
+ model.layers.7.self_attn.o_proj: 5
93
+ model.layers.8.self_attn.k_proj: 7
94
+ model.layers.30.mlp.gate_proj: 5
95
+ model.layers.23.mlp.up_proj: 5
96
+ model.layers.27.self_attn.o_proj: 5
97
+ model.layers.28.mlp.down_proj: 5
98
+ model.layers.30.self_attn.v_proj: 7
99
+ model.layers.3.self_attn.q_proj: 6
100
+ model.layers.10.self_attn.v_proj: 7
101
+ model.layers.10.mlp.up_proj: 4
102
+ model.layers.6.self_attn.v_proj: 8
103
+ model.layers.5.self_attn.o_proj: 5
104
+ model.layers.6.self_attn.o_proj: 4
105
+ model.layers.7.mlp.gate_proj: 5
106
+ model.layers.12.mlp.down_proj: 5
107
+ model.layers.23.self_attn.o_proj: 5
108
+ model.layers.8.self_attn.o_proj: 6
109
+ model.layers.8.self_attn.v_proj: 7
110
+ model.layers.10.mlp.gate_proj: 4
111
+ model.layers.4.self_attn.v_proj: 5
112
+ model.layers.10.self_attn.k_proj: 7
113
+ model.layers.19.self_attn.o_proj: 5
114
+ model.layers.35.mlp.gate_proj: 5
115
+ model.layers.5.self_attn.v_proj: 8
116
+ model.layers.4.self_attn.k_proj: 5
117
+ model.layers.4.self_attn.o_proj: 6
118
+ model.layers.4.mlp.down_proj: 4
119
+ model.layers.5.self_attn.q_proj: 5
120
+ model.layers.5.mlp.down_proj: 4
121
+ model.layers.7.self_attn.k_proj: 8
122
+ model.layers.7.mlp.up_proj: 5
123
+ model.layers.5.self_attn.k_proj: 8
124
+ model.layers.6.mlp.up_proj: 4
125
+ model.layers.9.self_attn.v_proj: 7
126
+ model.layers.9.mlp.down_proj: 4
127
+ model.layers.4.mlp.up_proj: 4
128
+ model.layers.9.mlp.gate_proj: 4
129
+ model.layers.6.self_attn.q_proj: 5
130
+ model.layers.6.self_attn.k_proj: 8
131
+ model.layers.8.mlp.up_proj: 4
132
+ model.layers.9.self_attn.o_proj: 5
133
+ model.layers.18.mlp.up_proj: 5
134
+ model.layers.20.self_attn.v_proj: 8
135
+ model.layers.23.self_attn.q_proj: 5
136
+ model.layers.13.self_attn.v_proj: 8
137
+ model.layers.27.self_attn.k_proj: 7
138
+ model.layers.27.mlp.gate_proj: 5
139
+ model.layers.30.mlp.down_proj: 5
140
+ model.layers.34.mlp.down_proj: 5
141
+ model.layers.20.mlp.gate_proj: 4
142
+ model.layers.35.self_attn.q_proj: 7
143
+ model.layers.15.self_attn.v_proj: 8
144
+ model.layers.29.mlp.gate_proj: 6
145
+ model.layers.17.mlp.up_proj: 4
146
+ model.layers.22.mlp.down_proj: 5
147
+ model.layers.28.self_attn.v_proj: 7
148
+ model.layers.38.mlp.up_proj: 6
149
+ model.layers.39.self_attn.q_proj: 6
150
+ model.layers.11.self_attn.v_proj: 7
151
+ model.layers.12.self_attn.k_proj: 7
152
+ model.layers.16.mlp.up_proj: 4
153
+ model.layers.18.self_attn.o_proj: 6
154
+ model.layers.20.self_attn.o_proj: 4
155
+ model.layers.21.self_attn.o_proj: 5
156
+ model.layers.29.self_attn.k_proj: 8
157
+ model.layers.28.self_attn.q_proj: 5
158
+ model.layers.28.mlp.up_proj: 5
159
+ model.layers.38.self_attn.o_proj: 4
160
+ model.layers.14.mlp.down_proj: 4
161
+ model.layers.27.mlp.up_proj: 5
162
+ model.layers.22.self_attn.q_proj: 5
163
+ model.layers.33.mlp.gate_proj: 6
164
+ model.layers.16.self_attn.k_proj: 7
165
+ model.layers.16.self_attn.v_proj: 7
166
+ model.layers.25.self_attn.o_proj: 4
167
+ model.layers.18.self_attn.k_proj: 8
168
+ model.layers.16.mlp.gate_proj: 4
169
+ model.layers.19.mlp.up_proj: 4
170
+ model.layers.26.self_attn.k_proj: 6
171
+ model.layers.31.self_attn.q_proj: 5
172
+ model.layers.11.mlp.down_proj: 4
173
+ model.layers.12.mlp.up_proj: 4
174
+ model.layers.15.self_attn.q_proj: 5
175
+ model.layers.18.mlp.gate_proj: 5
176
+ model.layers.10.self_attn.o_proj: 5
177
+ model.layers.17.self_attn.o_proj: 4
178
+ model.layers.22.mlp.gate_proj: 5
179
+ model.layers.27.self_attn.v_proj: 7
180
+ model.layers.34.self_attn.k_proj: 6
181
+ model.layers.34.self_attn.o_proj: 5
182
+ model.layers.37.self_attn.q_proj: 6
183
+ model.layers.14.self_attn.v_proj: 8
184
+ model.layers.16.self_attn.q_proj: 5
185
+ model.layers.17.self_attn.v_proj: 8
186
+ model.layers.23.mlp.gate_proj: 5
187
+ model.layers.24.self_attn.v_proj: 8
188
+ model.layers.25.self_attn.k_proj: 8
189
+ model.layers.29.self_attn.o_proj: 5
190
+ model.layers.31.self_attn.v_proj: 7
191
+ model.layers.33.mlp.up_proj: 6
192
+ model.layers.39.self_attn.o_proj: 6
193
+ model.layers.11.mlp.up_proj: 4
194
+ model.layers.12.mlp.gate_proj: 4
195
+ model.layers.14.self_attn.o_proj: 5
196
+ model.layers.17.self_attn.q_proj: 5
197
+ model.layers.17.mlp.gate_proj: 4
198
+ model.layers.20.mlp.down_proj: 4
199
+ model.layers.32.mlp.down_proj: 4
200
+ model.layers.39.self_attn.k_proj: 8
201
+ model.layers.11.self_attn.q_proj: 5
202
+ model.layers.12.self_attn.q_proj: 5
203
+ model.layers.13.self_attn.k_proj: 8
204
+ model.layers.14.self_attn.q_proj: 4
205
+ model.layers.14.mlp.up_proj: 4
206
+ model.layers.15.mlp.gate_proj: 5
207
+ model.layers.19.self_attn.k_proj: 7
208
+ model.layers.37.self_attn.v_proj: 8
209
+ model.layers.11.self_attn.k_proj: 7
210
+ model.layers.18.self_attn.q_proj: 4
211
+ model.layers.27.self_attn.q_proj: 6
212
+ model.layers.36.mlp.up_proj: 5
213
+ model.layers.37.self_attn.o_proj: 5
214
+ model.layers.38.self_attn.v_proj: 8
215
+ model.layers.10.mlp.down_proj: 4
216
+ model.layers.12.self_attn.v_proj: 7
217
+ model.layers.13.self_attn.q_proj: 5
218
+ model.layers.13.mlp.gate_proj: 4
219
+ model.layers.14.mlp.gate_proj: 4
220
+ model.layers.15.mlp.down_proj: 4
221
+ model.layers.22.self_attn.v_proj: 7
222
+ model.layers.23.self_attn.k_proj: 8
223
+ model.layers.11.mlp.gate_proj: 4
224
+ model.layers.21.self_attn.q_proj: 5
225
+ model.layers.32.self_attn.q_proj: 7
226
+ model.layers.37.self_attn.k_proj: 8
227
+ model.layers.37.mlp.up_proj: 6
228
+ model.layers.11.self_attn.o_proj: 4
229
+ model.layers.12.self_attn.o_proj: 5
230
+ model.layers.13.self_attn.o_proj: 6
231
+ model.layers.13.mlp.up_proj: 4
232
+ model.layers.15.mlp.up_proj: 5
233
+ model.layers.17.self_attn.k_proj: 8
234
+ model.layers.18.self_attn.v_proj: 8
235
+ model.layers.18.mlp.down_proj: 4
236
+ model.layers.20.self_attn.k_proj: 8
237
+ model.layers.21.self_attn.k_proj: 5
238
+ model.layers.28.self_attn.k_proj: 7
239
+ model.layers.29.self_attn.q_proj: 5
240
+ model.layers.31.self_attn.k_proj: 7
241
+ model.layers.31.mlp.down_proj: 4
242
+ model.layers.32.self_attn.o_proj: 6
243
+ model.layers.33.self_attn.v_proj: 8
244
+ model.layers.37.mlp.down_proj: 5
245
+ model.layers.24.mlp.gate_proj: 5
246
+ model.layers.26.mlp.up_proj: 5
247
+ model.layers.23.mlp.down_proj: 5
248
+ model.layers.25.mlp.down_proj: 4
249
+ model.layers.32.mlp.up_proj: 6
250
+ model.layers.28.self_attn.o_proj: 6
251
+ model.layers.21.self_attn.v_proj: 5
252
+ model.layers.24.mlp.down_proj: 4
253
+ model.layers.17.mlp.down_proj: 5
254
+ model.layers.19.self_attn.v_proj: 7
255
+ model.layers.19.mlp.gate_proj: 4
256
+ model.layers.19.mlp.down_proj: 4
257
+ model.layers.21.mlp.up_proj: 4
258
+ model.layers.23.self_attn.v_proj: 8
259
+ model.layers.24.self_attn.q_proj: 6
260
+ model.layers.25.self_attn.q_proj: 5
261
+ model.layers.25.mlp.up_proj: 5
262
+ model.layers.26.self_attn.o_proj: 6
263
+ model.layers.26.mlp.down_proj: 5
264
+ model.layers.27.mlp.down_proj: 5
265
+ model.layers.30.self_attn.q_proj: 5
266
+ model.layers.31.self_attn.o_proj: 6
267
+ model.layers.31.mlp.up_proj: 6
268
+ model.layers.36.self_attn.v_proj: 8
269
+ model.layers.22.self_attn.k_proj: 7
270
+ model.layers.22.mlp.up_proj: 5
271
+ model.layers.24.self_attn.o_proj: 5
272
+ model.layers.29.self_attn.v_proj: 8
273
+ model.layers.32.self_attn.v_proj: 7
274
+ model.layers.33.self_attn.o_proj: 6
275
+ model.layers.34.mlp.gate_proj: 6
276
+ model.layers.37.mlp.gate_proj: 6
277
+ model.layers.39.self_attn.v_proj: 8
278
+ model.layers.39.mlp.gate_proj: 6
279
+ model.layers.24.self_attn.k_proj: 8
280
+ model.layers.25.self_attn.v_proj: 8
281
+ model.layers.25.mlp.gate_proj: 5
282
+ model.layers.29.mlp.up_proj: 6
283
+ model.layers.30.self_attn.k_proj: 7
284
+ model.layers.30.self_attn.o_proj: 6
285
+ model.layers.30.mlp.up_proj: 5
286
+ model.layers.26.self_attn.v_proj: 6
287
+ model.layers.32.mlp.gate_proj: 6
288
+ model.layers.35.self_attn.v_proj: 7
289
+ model.layers.35.mlp.up_proj: 5
290
+ model.layers.38.self_attn.q_proj: 7
291
+ model.layers.38.mlp.gate_proj: 6
292
+ model.layers.26.mlp.gate_proj: 5
293
+ model.layers.31.mlp.gate_proj: 6
294
+ model.layers.33.mlp.down_proj: 4
295
+ model.layers.36.self_attn.o_proj: 6
296
+ model.layers.39.mlp.down_proj: 5
297
+ model.layers.28.mlp.gate_proj: 5
298
+ model.layers.35.mlp.down_proj: 5
299
+ model.layers.39.mlp.up_proj: 6
300
+ model.layers.33.self_attn.q_proj: 5
301
+ model.layers.34.self_attn.q_proj: 6
302
+ model.layers.34.self_attn.v_proj: 6
303
+ model.layers.34.mlp.up_proj: 5
304
+ model.layers.35.self_attn.k_proj: 7
305
+ model.layers.36.self_attn.q_proj: 7
306
+ model.layers.36.self_attn.k_proj: 8
307
+ model.layers.36.mlp.gate_proj: 5
308
+ model.layers.36.mlp.down_proj: 5
309
+ model.layers.35.self_attn.o_proj: 5
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bsearch_kl0.005_eap0.99_sha_bw4.98_4-5-6-7-8bit_seed42/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ # Quantized Model Checkpoint
2
+
3
+ **Base model:** Qwen/Qwen3-32B
4
+
5
+ **Average bitwidth:** 8.156
6
+
7
+ See `quantization_config.txt` for full configuration details.
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 25600,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention"
80
+ ],
81
+ "max_position_embeddings": 40960,
82
+ "max_window_layers": 64,
83
+ "model_type": "qwen3",
84
+ "num_attention_heads": 64,
85
+ "num_hidden_layers": 64,
86
+ "num_key_value_heads": 8,
87
+ "rms_norm_eps": 1e-06,
88
+ "rope_scaling": null,
89
+ "rope_theta": 1000000,
90
+ "sliding_window": null,
91
+ "tie_word_embeddings": false,
92
+ "transformers_version": "4.57.3",
93
+ "use_cache": false,
94
+ "use_sliding_window": false,
95
+ "vocab_size": 151936
96
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/humming_online_quant_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "quant_method": "gptq",
3
+ "bits": 8,
4
+ "group_size": 128
5
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/model.safetensors.index.json ADDED
@@ -0,0 +1,715 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 32762123264,
4
+ "total_size": 65524246528
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00014-of-00014.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
46
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
57
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
68
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
79
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
90
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
101
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
112
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
123
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
134
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
145
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
156
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
167
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
178
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
189
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
200
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
211
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
222
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
233
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
244
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
255
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
266
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
277
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
288
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
299
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
300
+ "model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
303
+ "model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
304
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
305
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
310
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
311
+ "model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
314
+ "model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
315
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
316
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
322
+ "model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
325
+ "model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
326
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
327
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
332
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
336
+ "model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
337
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
338
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
339
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
340
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
341
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
342
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
343
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
344
+ "model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
345
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
346
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
347
+ "model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
348
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
349
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
350
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
351
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
352
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
353
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
354
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
355
+ "model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
356
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
357
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
358
+ "model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
359
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
360
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
361
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
362
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
363
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
364
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
365
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
366
+ "model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
367
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
368
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
369
+ "model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
370
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
371
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
372
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
373
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
374
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
375
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
376
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
377
+ "model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
378
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
379
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
380
+ "model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
381
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
382
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
383
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
384
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
385
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
386
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
387
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
388
+ "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
389
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
390
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
391
+ "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
392
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
393
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
394
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
395
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
396
+ "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
397
+ "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
398
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
399
+ "model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
400
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
401
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
402
+ "model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
403
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
404
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
405
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
406
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
407
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
408
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
409
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
410
+ "model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
411
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
412
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
413
+ "model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
414
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
415
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
417
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
418
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
419
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
420
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
421
+ "model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
422
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
423
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
424
+ "model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
425
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
426
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
427
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
428
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
429
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
430
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
431
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
432
+ "model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
433
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
434
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
435
+ "model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
436
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
437
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
438
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
439
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
440
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
441
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
442
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
443
+ "model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
444
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
445
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
446
+ "model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
447
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
448
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
449
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
450
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
451
+ "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
452
+ "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
453
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
454
+ "model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
455
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
456
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
457
+ "model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
458
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
459
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
460
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
461
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
462
+ "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
463
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
464
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
465
+ "model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
466
+ "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
467
+ "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
468
+ "model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
469
+ "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
470
+ "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
471
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
472
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
473
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
474
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
475
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
476
+ "model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
477
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
478
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
479
+ "model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
480
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
481
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
482
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
483
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
484
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
485
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
486
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
487
+ "model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
488
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
489
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
490
+ "model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
491
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
492
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
493
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
494
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
495
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
496
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
497
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
498
+ "model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
499
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
500
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
501
+ "model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
502
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
503
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
504
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
505
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
506
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
507
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
508
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
509
+ "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
510
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
511
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
512
+ "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
513
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
514
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
515
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
516
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
517
+ "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
518
+ "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
519
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
520
+ "model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
521
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
522
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
523
+ "model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
524
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
525
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
526
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
527
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
528
+ "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
529
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
530
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
531
+ "model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
532
+ "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
533
+ "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
534
+ "model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
535
+ "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
536
+ "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
537
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
538
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
539
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
540
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
541
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
542
+ "model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
543
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
544
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
545
+ "model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
546
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
547
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
549
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
550
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
551
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
552
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
553
+ "model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
554
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
555
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
556
+ "model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
557
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
558
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
559
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
560
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
561
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
562
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
563
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
564
+ "model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
565
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
566
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
567
+ "model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
568
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
569
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
570
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
571
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
572
+ "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
573
+ "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
574
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
575
+ "model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
576
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
577
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
578
+ "model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
579
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
580
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
581
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
582
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
583
+ "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
584
+ "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
585
+ "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
586
+ "model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
587
+ "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
588
+ "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
589
+ "model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
590
+ "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
591
+ "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
592
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
593
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
594
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
595
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
596
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
597
+ "model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
598
+ "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
599
+ "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
600
+ "model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
601
+ "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
602
+ "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
603
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
604
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
605
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
606
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
607
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
608
+ "model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
609
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
610
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
611
+ "model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
612
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
613
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
614
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
615
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
616
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
617
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
618
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
619
+ "model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
620
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
621
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
622
+ "model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
623
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
624
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
625
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
626
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
627
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
628
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
629
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
630
+ "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
631
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
632
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
633
+ "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
634
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
635
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
636
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
637
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
638
+ "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
639
+ "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
640
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
641
+ "model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
642
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
643
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
644
+ "model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
645
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
646
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
647
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
648
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
649
+ "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
650
+ "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
651
+ "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
652
+ "model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
653
+ "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
654
+ "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
655
+ "model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
656
+ "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
657
+ "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
658
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
659
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
660
+ "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
661
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
662
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
663
+ "model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
664
+ "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
665
+ "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
666
+ "model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
667
+ "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
668
+ "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
669
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
670
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
671
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
672
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
673
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
674
+ "model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
675
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
676
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
677
+ "model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
678
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
679
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
+ "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
686
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
+ "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
689
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
691
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
692
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
693
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
694
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
695
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
696
+ "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
697
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
698
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
699
+ "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
700
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
701
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
702
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
703
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
704
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
705
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
706
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
707
+ "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
708
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
709
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
710
+ "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
711
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
712
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
713
+ "model.norm.weight": "model-00014-of-00014.safetensors"
714
+ }
715
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/quantization_config.txt ADDED
@@ -0,0 +1,285 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model: Qwen/Qwen3-32B
2
+ # Average bitwidth: 8.156
3
+ # Bitwidth distribution:
4
+ # 8-bit: 280 layers (100.0%)
5
+ #
6
+ model.layers.0.mlp.down_proj: 8
7
+ model.layers.2.self_attn.k_proj: 8
8
+ model.layers.0.self_attn.k_proj: 8
9
+ model.layers.0.self_attn.v_proj: 8
10
+ model.layers.2.mlp.gate_proj: 8
11
+ model.layers.1.mlp.down_proj: 8
12
+ model.layers.0.mlp.up_proj: 8
13
+ model.layers.1.self_attn.v_proj: 8
14
+ model.layers.2.mlp.up_proj: 8
15
+ model.layers.0.mlp.gate_proj: 8
16
+ model.layers.1.self_attn.q_proj: 8
17
+ model.layers.0.self_attn.o_proj: 8
18
+ model.layers.1.self_attn.k_proj: 8
19
+ model.layers.2.self_attn.q_proj: 8
20
+ model.layers.2.self_attn.v_proj: 8
21
+ model.layers.2.self_attn.o_proj: 8
22
+ model.layers.0.self_attn.q_proj: 8
23
+ model.layers.1.mlp.up_proj: 8
24
+ model.layers.1.self_attn.o_proj: 8
25
+ model.layers.1.mlp.gate_proj: 8
26
+ model.layers.7.self_attn.v_proj: 8
27
+ model.layers.6.mlp.gate_proj: 8
28
+ model.layers.9.self_attn.k_proj: 8
29
+ model.layers.7.self_attn.q_proj: 8
30
+ model.layers.21.mlp.gate_proj: 8
31
+ model.layers.38.self_attn.k_proj: 8
32
+ model.layers.32.self_attn.k_proj: 8
33
+ model.layers.29.mlp.down_proj: 8
34
+ model.layers.19.self_attn.q_proj: 8
35
+ model.layers.33.self_attn.k_proj: 8
36
+ model.layers.15.self_attn.k_proj: 8
37
+ model.layers.21.mlp.down_proj: 8
38
+ model.layers.3.self_attn.o_proj: 8
39
+ model.layers.3.mlp.up_proj: 8
40
+ model.layers.2.mlp.down_proj: 8
41
+ model.layers.3.mlp.down_proj: 8
42
+ model.layers.8.self_attn.q_proj: 8
43
+ model.layers.24.mlp.up_proj: 8
44
+ model.layers.5.mlp.gate_proj: 8
45
+ model.layers.9.self_attn.q_proj: 8
46
+ model.layers.8.mlp.down_proj: 8
47
+ model.layers.7.mlp.down_proj: 8
48
+ model.layers.8.mlp.gate_proj: 8
49
+ model.layers.3.self_attn.v_proj: 8
50
+ model.layers.6.mlp.down_proj: 8
51
+ model.layers.13.mlp.down_proj: 8
52
+ model.layers.16.mlp.down_proj: 8
53
+ model.layers.22.self_attn.o_proj: 8
54
+ model.layers.38.mlp.down_proj: 8
55
+ model.layers.3.mlp.gate_proj: 8
56
+ model.layers.10.self_attn.q_proj: 8
57
+ model.layers.14.self_attn.k_proj: 8
58
+ model.layers.16.self_attn.o_proj: 8
59
+ model.layers.20.mlp.up_proj: 8
60
+ model.layers.26.self_attn.q_proj: 8
61
+ model.layers.4.self_attn.q_proj: 8
62
+ model.layers.9.mlp.up_proj: 8
63
+ model.layers.15.self_attn.o_proj: 8
64
+ model.layers.20.self_attn.q_proj: 8
65
+ model.layers.3.self_attn.k_proj: 8
66
+ model.layers.4.mlp.gate_proj: 8
67
+ model.layers.5.mlp.up_proj: 8
68
+ model.layers.7.self_attn.o_proj: 8
69
+ model.layers.8.self_attn.k_proj: 8
70
+ model.layers.30.mlp.gate_proj: 8
71
+ model.layers.23.mlp.up_proj: 8
72
+ model.layers.27.self_attn.o_proj: 8
73
+ model.layers.28.mlp.down_proj: 8
74
+ model.layers.30.self_attn.v_proj: 8
75
+ model.layers.3.self_attn.q_proj: 8
76
+ model.layers.10.self_attn.v_proj: 8
77
+ model.layers.10.mlp.up_proj: 8
78
+ model.layers.6.self_attn.v_proj: 8
79
+ model.layers.5.self_attn.o_proj: 8
80
+ model.layers.6.self_attn.o_proj: 8
81
+ model.layers.7.mlp.gate_proj: 8
82
+ model.layers.12.mlp.down_proj: 8
83
+ model.layers.23.self_attn.o_proj: 8
84
+ model.layers.8.self_attn.o_proj: 8
85
+ model.layers.8.self_attn.v_proj: 8
86
+ model.layers.10.mlp.gate_proj: 8
87
+ model.layers.4.self_attn.v_proj: 8
88
+ model.layers.10.self_attn.k_proj: 8
89
+ model.layers.19.self_attn.o_proj: 8
90
+ model.layers.35.mlp.gate_proj: 8
91
+ model.layers.5.self_attn.v_proj: 8
92
+ model.layers.4.self_attn.k_proj: 8
93
+ model.layers.4.self_attn.o_proj: 8
94
+ model.layers.4.mlp.down_proj: 8
95
+ model.layers.5.self_attn.q_proj: 8
96
+ model.layers.5.mlp.down_proj: 8
97
+ model.layers.7.self_attn.k_proj: 8
98
+ model.layers.7.mlp.up_proj: 8
99
+ model.layers.5.self_attn.k_proj: 8
100
+ model.layers.6.mlp.up_proj: 8
101
+ model.layers.9.self_attn.v_proj: 8
102
+ model.layers.9.mlp.down_proj: 8
103
+ model.layers.4.mlp.up_proj: 8
104
+ model.layers.9.mlp.gate_proj: 8
105
+ model.layers.6.self_attn.q_proj: 8
106
+ model.layers.6.self_attn.k_proj: 8
107
+ model.layers.8.mlp.up_proj: 8
108
+ model.layers.9.self_attn.o_proj: 8
109
+ model.layers.18.mlp.up_proj: 8
110
+ model.layers.20.self_attn.v_proj: 8
111
+ model.layers.23.self_attn.q_proj: 8
112
+ model.layers.13.self_attn.v_proj: 8
113
+ model.layers.27.self_attn.k_proj: 8
114
+ model.layers.27.mlp.gate_proj: 8
115
+ model.layers.30.mlp.down_proj: 8
116
+ model.layers.34.mlp.down_proj: 8
117
+ model.layers.20.mlp.gate_proj: 8
118
+ model.layers.35.self_attn.q_proj: 8
119
+ model.layers.15.self_attn.v_proj: 8
120
+ model.layers.29.mlp.gate_proj: 8
121
+ model.layers.17.mlp.up_proj: 8
122
+ model.layers.22.mlp.down_proj: 8
123
+ model.layers.28.self_attn.v_proj: 8
124
+ model.layers.38.mlp.up_proj: 8
125
+ model.layers.39.self_attn.q_proj: 8
126
+ model.layers.11.self_attn.v_proj: 8
127
+ model.layers.12.self_attn.k_proj: 8
128
+ model.layers.16.mlp.up_proj: 8
129
+ model.layers.18.self_attn.o_proj: 8
130
+ model.layers.20.self_attn.o_proj: 8
131
+ model.layers.21.self_attn.o_proj: 8
132
+ model.layers.29.self_attn.k_proj: 8
133
+ model.layers.28.self_attn.q_proj: 8
134
+ model.layers.28.mlp.up_proj: 8
135
+ model.layers.38.self_attn.o_proj: 8
136
+ model.layers.14.mlp.down_proj: 8
137
+ model.layers.27.mlp.up_proj: 8
138
+ model.layers.22.self_attn.q_proj: 8
139
+ model.layers.33.mlp.gate_proj: 8
140
+ model.layers.16.self_attn.k_proj: 8
141
+ model.layers.16.self_attn.v_proj: 8
142
+ model.layers.25.self_attn.o_proj: 8
143
+ model.layers.18.self_attn.k_proj: 8
144
+ model.layers.16.mlp.gate_proj: 8
145
+ model.layers.19.mlp.up_proj: 8
146
+ model.layers.26.self_attn.k_proj: 8
147
+ model.layers.31.self_attn.q_proj: 8
148
+ model.layers.11.mlp.down_proj: 8
149
+ model.layers.12.mlp.up_proj: 8
150
+ model.layers.15.self_attn.q_proj: 8
151
+ model.layers.18.mlp.gate_proj: 8
152
+ model.layers.10.self_attn.o_proj: 8
153
+ model.layers.17.self_attn.o_proj: 8
154
+ model.layers.22.mlp.gate_proj: 8
155
+ model.layers.27.self_attn.v_proj: 8
156
+ model.layers.34.self_attn.k_proj: 8
157
+ model.layers.34.self_attn.o_proj: 8
158
+ model.layers.37.self_attn.q_proj: 8
159
+ model.layers.14.self_attn.v_proj: 8
160
+ model.layers.16.self_attn.q_proj: 8
161
+ model.layers.17.self_attn.v_proj: 8
162
+ model.layers.23.mlp.gate_proj: 8
163
+ model.layers.24.self_attn.v_proj: 8
164
+ model.layers.25.self_attn.k_proj: 8
165
+ model.layers.29.self_attn.o_proj: 8
166
+ model.layers.31.self_attn.v_proj: 8
167
+ model.layers.33.mlp.up_proj: 8
168
+ model.layers.39.self_attn.o_proj: 8
169
+ model.layers.11.mlp.up_proj: 8
170
+ model.layers.12.mlp.gate_proj: 8
171
+ model.layers.14.self_attn.o_proj: 8
172
+ model.layers.17.self_attn.q_proj: 8
173
+ model.layers.17.mlp.gate_proj: 8
174
+ model.layers.20.mlp.down_proj: 8
175
+ model.layers.32.mlp.down_proj: 8
176
+ model.layers.39.self_attn.k_proj: 8
177
+ model.layers.11.self_attn.q_proj: 8
178
+ model.layers.12.self_attn.q_proj: 8
179
+ model.layers.13.self_attn.k_proj: 8
180
+ model.layers.14.self_attn.q_proj: 8
181
+ model.layers.14.mlp.up_proj: 8
182
+ model.layers.15.mlp.gate_proj: 8
183
+ model.layers.19.self_attn.k_proj: 8
184
+ model.layers.37.self_attn.v_proj: 8
185
+ model.layers.11.self_attn.k_proj: 8
186
+ model.layers.18.self_attn.q_proj: 8
187
+ model.layers.27.self_attn.q_proj: 8
188
+ model.layers.36.mlp.up_proj: 8
189
+ model.layers.37.self_attn.o_proj: 8
190
+ model.layers.38.self_attn.v_proj: 8
191
+ model.layers.10.mlp.down_proj: 8
192
+ model.layers.12.self_attn.v_proj: 8
193
+ model.layers.13.self_attn.q_proj: 8
194
+ model.layers.13.mlp.gate_proj: 8
195
+ model.layers.14.mlp.gate_proj: 8
196
+ model.layers.15.mlp.down_proj: 8
197
+ model.layers.22.self_attn.v_proj: 8
198
+ model.layers.23.self_attn.k_proj: 8
199
+ model.layers.11.mlp.gate_proj: 8
200
+ model.layers.21.self_attn.q_proj: 8
201
+ model.layers.32.self_attn.q_proj: 8
202
+ model.layers.37.self_attn.k_proj: 8
203
+ model.layers.37.mlp.up_proj: 8
204
+ model.layers.11.self_attn.o_proj: 8
205
+ model.layers.12.self_attn.o_proj: 8
206
+ model.layers.13.self_attn.o_proj: 8
207
+ model.layers.13.mlp.up_proj: 8
208
+ model.layers.15.mlp.up_proj: 8
209
+ model.layers.17.self_attn.k_proj: 8
210
+ model.layers.18.self_attn.v_proj: 8
211
+ model.layers.18.mlp.down_proj: 8
212
+ model.layers.20.self_attn.k_proj: 8
213
+ model.layers.21.self_attn.k_proj: 8
214
+ model.layers.28.self_attn.k_proj: 8
215
+ model.layers.29.self_attn.q_proj: 8
216
+ model.layers.31.self_attn.k_proj: 8
217
+ model.layers.31.mlp.down_proj: 8
218
+ model.layers.32.self_attn.o_proj: 8
219
+ model.layers.33.self_attn.v_proj: 8
220
+ model.layers.37.mlp.down_proj: 8
221
+ model.layers.24.mlp.gate_proj: 8
222
+ model.layers.26.mlp.up_proj: 8
223
+ model.layers.23.mlp.down_proj: 8
224
+ model.layers.25.mlp.down_proj: 8
225
+ model.layers.32.mlp.up_proj: 8
226
+ model.layers.28.self_attn.o_proj: 8
227
+ model.layers.21.self_attn.v_proj: 8
228
+ model.layers.24.mlp.down_proj: 8
229
+ model.layers.17.mlp.down_proj: 8
230
+ model.layers.19.self_attn.v_proj: 8
231
+ model.layers.19.mlp.gate_proj: 8
232
+ model.layers.19.mlp.down_proj: 8
233
+ model.layers.21.mlp.up_proj: 8
234
+ model.layers.23.self_attn.v_proj: 8
235
+ model.layers.24.self_attn.q_proj: 8
236
+ model.layers.25.self_attn.q_proj: 8
237
+ model.layers.25.mlp.up_proj: 8
238
+ model.layers.26.self_attn.o_proj: 8
239
+ model.layers.26.mlp.down_proj: 8
240
+ model.layers.27.mlp.down_proj: 8
241
+ model.layers.30.self_attn.q_proj: 8
242
+ model.layers.31.self_attn.o_proj: 8
243
+ model.layers.31.mlp.up_proj: 8
244
+ model.layers.36.self_attn.v_proj: 8
245
+ model.layers.22.self_attn.k_proj: 8
246
+ model.layers.22.mlp.up_proj: 8
247
+ model.layers.24.self_attn.o_proj: 8
248
+ model.layers.29.self_attn.v_proj: 8
249
+ model.layers.32.self_attn.v_proj: 8
250
+ model.layers.33.self_attn.o_proj: 8
251
+ model.layers.34.mlp.gate_proj: 8
252
+ model.layers.37.mlp.gate_proj: 8
253
+ model.layers.39.self_attn.v_proj: 8
254
+ model.layers.39.mlp.gate_proj: 8
255
+ model.layers.24.self_attn.k_proj: 8
256
+ model.layers.25.self_attn.v_proj: 8
257
+ model.layers.25.mlp.gate_proj: 8
258
+ model.layers.29.mlp.up_proj: 8
259
+ model.layers.30.self_attn.k_proj: 8
260
+ model.layers.30.self_attn.o_proj: 8
261
+ model.layers.30.mlp.up_proj: 8
262
+ model.layers.26.self_attn.v_proj: 8
263
+ model.layers.32.mlp.gate_proj: 8
264
+ model.layers.35.self_attn.v_proj: 8
265
+ model.layers.35.mlp.up_proj: 8
266
+ model.layers.38.self_attn.q_proj: 8
267
+ model.layers.38.mlp.gate_proj: 8
268
+ model.layers.26.mlp.gate_proj: 8
269
+ model.layers.31.mlp.gate_proj: 8
270
+ model.layers.33.mlp.down_proj: 8
271
+ model.layers.36.self_attn.o_proj: 8
272
+ model.layers.39.mlp.down_proj: 8
273
+ model.layers.28.mlp.gate_proj: 8
274
+ model.layers.35.mlp.down_proj: 8
275
+ model.layers.39.mlp.up_proj: 8
276
+ model.layers.33.self_attn.q_proj: 8
277
+ model.layers.34.self_attn.q_proj: 8
278
+ model.layers.34.self_attn.v_proj: 8
279
+ model.layers.34.mlp.up_proj: 8
280
+ model.layers.35.self_attn.k_proj: 8
281
+ model.layers.36.self_attn.q_proj: 8
282
+ model.layers.36.self_attn.k_proj: 8
283
+ model.layers.36.mlp.gate_proj: 8
284
+ model.layers.36.mlp.down_proj: 8
285
+ model.layers.35.self_attn.o_proj: 8
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
humming/Qwen3-32B/Qwen3-32B/ll_bw8.16_8bit/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/config.json CHANGED
@@ -64,866 +64,5 @@
64
  "transformers_version": "4.57.3",
65
  "use_cache": false,
66
  "use_sliding_window": false,
67
- "vocab_size": 151936,
68
- "quantization_config": {
69
- "quant_method": "gptq",
70
- "weight_scale_type": "float16",
71
- "input_type": "float16",
72
- "has_global_scale": false,
73
- "weight_type": "int8",
74
- "has_dynamic_zp": true,
75
- "weight_scale_group_size": 128,
76
- "dynamic": {
77
- "+:model\\.layers\\.22\\.self_attn\\.o_proj": {
78
- "weight_type": "int6",
79
- "has_dynamic_zp": true,
80
- "weight_scale_group_size": 128
81
- },
82
- "+:model\\.layers\\.4\\.self_attn\\.o_proj": {
83
- "weight_type": "int6",
84
- "has_dynamic_zp": true,
85
- "weight_scale_group_size": 128
86
- },
87
- "+:model\\.layers\\.1\\.mlp\\.down_proj": {
88
- "weight_type": "int4",
89
- "has_dynamic_zp": true,
90
- "weight_scale_group_size": 128
91
- },
92
- "+:model\\.layers\\.11\\.mlp\\.up_proj": {
93
- "weight_type": "int6",
94
- "has_dynamic_zp": true,
95
- "weight_scale_group_size": 128
96
- },
97
- "+:model\\.layers\\.14\\.self_attn\\.q_proj": {
98
- "weight_type": "int7",
99
- "has_dynamic_zp": true,
100
- "weight_scale_group_size": 128
101
- },
102
- "+:model\\.layers\\.17\\.mlp\\.down_proj": {
103
- "weight_type": "int5",
104
- "has_dynamic_zp": true,
105
- "weight_scale_group_size": 128
106
- },
107
- "+:model\\.layers\\.33\\.mlp\\.gate_proj": {
108
- "weight_type": "int5",
109
- "has_dynamic_zp": true,
110
- "weight_scale_group_size": 128
111
- },
112
- "+:model\\.layers\\.27\\.mlp\\.gate_proj": {
113
- "weight_type": "int6",
114
- "has_dynamic_zp": true,
115
- "weight_scale_group_size": 128
116
- },
117
- "+:model\\.layers\\.2\\.mlp\\.up_proj": {
118
- "weight_type": "int5",
119
- "has_dynamic_zp": true,
120
- "weight_scale_group_size": 128
121
- },
122
- "+:model\\.layers\\.15\\.self_attn\\.q_proj": {
123
- "weight_type": "int7",
124
- "has_dynamic_zp": true,
125
- "weight_scale_group_size": 128
126
- },
127
- "+:model\\.layers\\.23\\.self_attn\\.o_proj": {
128
- "weight_type": "int7",
129
- "has_dynamic_zp": true,
130
- "weight_scale_group_size": 128
131
- },
132
- "+:model\\.layers\\.21\\.mlp\\.up_proj": {
133
- "weight_type": "int5",
134
- "has_dynamic_zp": true,
135
- "weight_scale_group_size": 128
136
- },
137
- "+:model\\.layers\\.4\\.mlp\\.down_proj": {
138
- "weight_type": "int5",
139
- "has_dynamic_zp": true,
140
- "weight_scale_group_size": 128
141
- },
142
- "+:model\\.layers\\.5\\.self_attn\\.o_proj": {
143
- "weight_type": "int6",
144
- "has_dynamic_zp": true,
145
- "weight_scale_group_size": 128
146
- },
147
- "+:model\\.layers\\.31\\.mlp\\.up_proj": {
148
- "weight_type": "int5",
149
- "has_dynamic_zp": true,
150
- "weight_scale_group_size": 128
151
- },
152
- "+:model\\.layers\\.22\\.mlp\\.gate_proj": {
153
- "weight_type": "int5",
154
- "has_dynamic_zp": true,
155
- "weight_scale_group_size": 128
156
- },
157
- "+:model\\.layers\\.8\\.mlp\\.gate_proj": {
158
- "weight_type": "int5",
159
- "has_dynamic_zp": true,
160
- "weight_scale_group_size": 128
161
- },
162
- "+:model\\.layers\\.12\\.mlp\\.down_proj": {
163
- "weight_type": "int5",
164
- "has_dynamic_zp": true,
165
- "weight_scale_group_size": 128
166
- },
167
- "+:model\\.layers\\.7\\.mlp\\.gate_proj": {
168
- "weight_type": "int5",
169
- "has_dynamic_zp": true,
170
- "weight_scale_group_size": 128
171
- },
172
- "+:model\\.layers\\.35\\.self_attn\\.o_proj": {
173
- "weight_type": "int6",
174
- "has_dynamic_zp": true,
175
- "weight_scale_group_size": 128
176
- },
177
- "+:model\\.layers\\.6\\.self_attn\\.o_proj": {
178
- "weight_type": "int6",
179
- "has_dynamic_zp": true,
180
- "weight_scale_group_size": 128
181
- },
182
- "+:model\\.layers\\.20\\.self_attn\\.o_proj": {
183
- "weight_type": "int6",
184
- "has_dynamic_zp": true,
185
- "weight_scale_group_size": 128
186
- },
187
- "+:model\\.layers\\.13\\.mlp\\.up_proj": {
188
- "weight_type": "int6",
189
- "has_dynamic_zp": true,
190
- "weight_scale_group_size": 128
191
- },
192
- "+:model\\.layers\\.35\\.mlp\\.down_proj": {
193
- "weight_type": "int6",
194
- "has_dynamic_zp": true,
195
- "weight_scale_group_size": 128
196
- },
197
- "+:model\\.layers\\.11\\.mlp\\.gate_proj": {
198
- "weight_type": "int6",
199
- "has_dynamic_zp": true,
200
- "weight_scale_group_size": 128
201
- },
202
- "+:model\\.layers\\.21\\.mlp\\.down_proj": {
203
- "weight_type": "int5",
204
- "has_dynamic_zp": true,
205
- "weight_scale_group_size": 128
206
- },
207
- "+:model\\.layers\\.33\\.mlp\\.up_proj": {
208
- "weight_type": "int5",
209
- "has_dynamic_zp": true,
210
- "weight_scale_group_size": 128
211
- },
212
- "+:model\\.layers\\.34\\.self_attn\\.o_proj": {
213
- "weight_type": "int6",
214
- "has_dynamic_zp": true,
215
- "weight_scale_group_size": 128
216
- },
217
- "+:model\\.layers\\.28\\.mlp\\.gate_proj": {
218
- "weight_type": "int5",
219
- "has_dynamic_zp": true,
220
- "weight_scale_group_size": 128
221
- },
222
- "+:model\\.layers\\.2\\.mlp\\.gate_proj": {
223
- "weight_type": "int5",
224
- "has_dynamic_zp": true,
225
- "weight_scale_group_size": 128
226
- },
227
- "+:model\\.layers\\.18\\.mlp\\.down_proj": {
228
- "weight_type": "int5",
229
- "has_dynamic_zp": true,
230
- "weight_scale_group_size": 128
231
- },
232
- "+:model\\.layers\\.17\\.self_attn\\.q_proj": {
233
- "weight_type": "int7",
234
- "has_dynamic_zp": true,
235
- "weight_scale_group_size": 128
236
- },
237
- "+:model\\.layers\\.0\\.mlp\\.up_proj": {
238
- "weight_type": "int4",
239
- "has_dynamic_zp": true,
240
- "weight_scale_group_size": 128
241
- },
242
- "+:model\\.layers\\.24\\.mlp\\.down_proj": {
243
- "weight_type": "int5",
244
- "has_dynamic_zp": true,
245
- "weight_scale_group_size": 128
246
- },
247
- "+:model\\.layers\\.23\\.mlp\\.up_proj": {
248
- "weight_type": "int5",
249
- "has_dynamic_zp": true,
250
- "weight_scale_group_size": 128
251
- },
252
- "+:model\\.layers\\.7\\.self_attn\\.o_proj": {
253
- "weight_type": "int6",
254
- "has_dynamic_zp": true,
255
- "weight_scale_group_size": 128
256
- },
257
- "+:model\\.layers\\.29\\.self_attn\\.q_proj": {
258
- "weight_type": "int7",
259
- "has_dynamic_zp": true,
260
- "weight_scale_group_size": 128
261
- },
262
- "+:model\\.layers\\.30\\.mlp\\.down_proj": {
263
- "weight_type": "int5",
264
- "has_dynamic_zp": true,
265
- "weight_scale_group_size": 128
266
- },
267
- "+:model\\.layers\\.14\\.mlp\\.gate_proj": {
268
- "weight_type": "int6",
269
- "has_dynamic_zp": true,
270
- "weight_scale_group_size": 128
271
- },
272
- "+:model\\.layers\\.21\\.self_attn\\.o_proj": {
273
- "weight_type": "int6",
274
- "has_dynamic_zp": true,
275
- "weight_scale_group_size": 128
276
- },
277
- "+:model\\.layers\\.6\\.mlp\\.up_proj": {
278
- "weight_type": "int6",
279
- "has_dynamic_zp": true,
280
- "weight_scale_group_size": 128
281
- },
282
- "+:model\\.layers\\.9\\.self_attn\\.q_proj": {
283
- "weight_type": "int7",
284
- "has_dynamic_zp": true,
285
- "weight_scale_group_size": 128
286
- },
287
- "+:model\\.layers\\.9\\.mlp\\.up_proj": {
288
- "weight_type": "int6",
289
- "has_dynamic_zp": true,
290
- "weight_scale_group_size": 128
291
- },
292
- "+:model\\.layers\\.1\\.self_attn\\.o_proj": {
293
- "weight_type": "int6",
294
- "has_dynamic_zp": true,
295
- "weight_scale_group_size": 128
296
- },
297
- "+:model\\.layers\\.27\\.self_attn\\.o_proj": {
298
- "weight_type": "int6",
299
- "has_dynamic_zp": true,
300
- "weight_scale_group_size": 128
301
- },
302
- "+:model\\.layers\\.19\\.self_attn\\.o_proj": {
303
- "weight_type": "int6",
304
- "has_dynamic_zp": true,
305
- "weight_scale_group_size": 128
306
- },
307
- "+:model\\.layers\\.0\\.mlp\\.gate_proj": {
308
- "weight_type": "int4",
309
- "has_dynamic_zp": true,
310
- "weight_scale_group_size": 128
311
- },
312
- "+:model\\.layers\\.11\\.self_attn\\.q_proj": {
313
- "weight_type": "int7",
314
- "has_dynamic_zp": true,
315
- "weight_scale_group_size": 128
316
- },
317
- "+:model\\.layers\\.25\\.mlp\\.up_proj": {
318
- "weight_type": "int5",
319
- "has_dynamic_zp": true,
320
- "weight_scale_group_size": 128
321
- },
322
- "+:model\\.layers\\.26\\.mlp\\.down_proj": {
323
- "weight_type": "int5",
324
- "has_dynamic_zp": true,
325
- "weight_scale_group_size": 128
326
- },
327
- "+:model\\.layers\\.35\\.mlp\\.up_proj": {
328
- "weight_type": "int7",
329
- "has_dynamic_zp": true,
330
- "weight_scale_group_size": 128
331
- },
332
- "+:model\\.layers\\.32\\.self_attn\\.o_proj": {
333
- "weight_type": "int6",
334
- "has_dynamic_zp": true,
335
- "weight_scale_group_size": 128
336
- },
337
- "+:model\\.layers\\.32\\.mlp\\.down_proj": {
338
- "weight_type": "int5",
339
- "has_dynamic_zp": true,
340
- "weight_scale_group_size": 128
341
- },
342
- "+:model\\.layers\\.16\\.mlp\\.gate_proj": {
343
- "weight_type": "int5",
344
- "has_dynamic_zp": true,
345
- "weight_scale_group_size": 128
346
- },
347
- "+:model\\.layers\\.15\\.mlp\\.up_proj": {
348
- "weight_type": "int5",
349
- "has_dynamic_zp": true,
350
- "weight_scale_group_size": 128
351
- },
352
- "+:model\\.layers\\.10\\.self_attn\\.q_proj": {
353
- "weight_type": "int7",
354
- "has_dynamic_zp": true,
355
- "weight_scale_group_size": 128
356
- },
357
- "+:model\\.layers\\.5\\.mlp\\.gate_proj": {
358
- "weight_type": "int5",
359
- "has_dynamic_zp": true,
360
- "weight_scale_group_size": 128
361
- },
362
- "+:model\\.layers\\.18\\.self_attn\\.o_proj": {
363
- "weight_type": "int6",
364
- "has_dynamic_zp": true,
365
- "weight_scale_group_size": 128
366
- },
367
- "+:model\\.layers\\.0\\.self_attn\\.o_proj": {
368
- "weight_type": "int6",
369
- "has_dynamic_zp": true,
370
- "weight_scale_group_size": 128
371
- },
372
- "+:model\\.layers\\.8\\.self_attn\\.q_proj": {
373
- "weight_type": "int7",
374
- "has_dynamic_zp": true,
375
- "weight_scale_group_size": 128
376
- },
377
- "+:model\\.layers\\.26\\.self_attn\\.o_proj": {
378
- "weight_type": "int6",
379
- "has_dynamic_zp": true,
380
- "weight_scale_group_size": 128
381
- },
382
- "+:model\\.layers\\.9\\.mlp\\.down_proj": {
383
- "weight_type": "int5",
384
- "has_dynamic_zp": true,
385
- "weight_scale_group_size": 128
386
- },
387
- "+:model\\.layers\\.13\\.mlp\\.gate_proj": {
388
- "weight_type": "int6",
389
- "has_dynamic_zp": true,
390
- "weight_scale_group_size": 128
391
- },
392
- "+:model\\.layers\\.33\\.self_attn\\.o_proj": {
393
- "weight_type": "int6",
394
- "has_dynamic_zp": true,
395
- "weight_scale_group_size": 128
396
- },
397
- "+:model\\.layers\\.23\\.mlp\\.down_proj": {
398
- "weight_type": "int5",
399
- "has_dynamic_zp": true,
400
- "weight_scale_group_size": 128
401
- },
402
- "+:model\\.layers\\.6\\.mlp\\.down_proj": {
403
- "weight_type": "int6",
404
- "has_dynamic_zp": true,
405
- "weight_scale_group_size": 128
406
- },
407
- "+:model\\.layers\\.30\\.self_attn\\.o_proj": {
408
- "weight_type": "int6",
409
- "has_dynamic_zp": true,
410
- "weight_scale_group_size": 128
411
- },
412
- "+:model\\.layers\\.4\\.mlp\\.up_proj": {
413
- "weight_type": "int5",
414
- "has_dynamic_zp": true,
415
- "weight_scale_group_size": 128
416
- },
417
- "+:model\\.layers\\.25\\.self_attn\\.o_proj": {
418
- "weight_type": "int6",
419
- "has_dynamic_zp": true,
420
- "weight_scale_group_size": 128
421
- },
422
- "+:model\\.layers\\.20\\.mlp\\.gate_proj": {
423
- "weight_type": "int5",
424
- "has_dynamic_zp": true,
425
- "weight_scale_group_size": 128
426
- },
427
- "+:model\\.layers\\.3\\.self_attn\\.o_proj": {
428
- "weight_type": "int6",
429
- "has_dynamic_zp": true,
430
- "weight_scale_group_size": 128
431
- },
432
- "+:model\\.layers\\.10\\.mlp\\.down_proj": {
433
- "weight_type": "int6",
434
- "has_dynamic_zp": true,
435
- "weight_scale_group_size": 128
436
- },
437
- "+:model\\.layers\\.34\\.mlp\\.gate_proj": {
438
- "weight_type": "int6",
439
- "has_dynamic_zp": true,
440
- "weight_scale_group_size": 128
441
- },
442
- "+:model\\.layers\\.13\\.self_attn\\.q_proj": {
443
- "weight_type": "int7",
444
- "has_dynamic_zp": true,
445
- "weight_scale_group_size": 128
446
- },
447
- "+:model\\.layers\\.28\\.mlp\\.up_proj": {
448
- "weight_type": "int5",
449
- "has_dynamic_zp": true,
450
- "weight_scale_group_size": 128
451
- },
452
- "+:model\\.layers\\.27\\.mlp\\.up_proj": {
453
- "weight_type": "int6",
454
- "has_dynamic_zp": true,
455
- "weight_scale_group_size": 128
456
- },
457
- "+:model\\.layers\\.3\\.mlp\\.down_proj": {
458
- "weight_type": "int5",
459
- "has_dynamic_zp": true,
460
- "weight_scale_group_size": 128
461
- },
462
- "+:model\\.layers\\.19\\.mlp\\.gate_proj": {
463
- "weight_type": "int5",
464
- "has_dynamic_zp": true,
465
- "weight_scale_group_size": 128
466
- },
467
- "+:model\\.layers\\.31\\.self_attn\\.o_proj": {
468
- "weight_type": "int6",
469
- "has_dynamic_zp": true,
470
- "weight_scale_group_size": 128
471
- },
472
- "+:model\\.layers\\.29\\.mlp\\.down_proj": {
473
- "weight_type": "int5",
474
- "has_dynamic_zp": true,
475
- "weight_scale_group_size": 128
476
- },
477
- "+:model\\.layers\\.18\\.mlp\\.up_proj": {
478
- "weight_type": "int5",
479
- "has_dynamic_zp": true,
480
- "weight_scale_group_size": 128
481
- },
482
- "+:model\\.layers\\.15\\.mlp\\.down_proj": {
483
- "weight_type": "int5",
484
- "has_dynamic_zp": true,
485
- "weight_scale_group_size": 128
486
- },
487
- "+:model\\.layers\\.17\\.mlp\\.up_proj": {
488
- "weight_type": "int5",
489
- "has_dynamic_zp": true,
490
- "weight_scale_group_size": 128
491
- },
492
- "+:model\\.layers\\.31\\.mlp\\.gate_proj": {
493
- "weight_type": "int5",
494
- "has_dynamic_zp": true,
495
- "weight_scale_group_size": 128
496
- },
497
- "+:model\\.layers\\.12\\.self_attn\\.q_proj": {
498
- "weight_type": "int7",
499
- "has_dynamic_zp": true,
500
- "weight_scale_group_size": 128
501
- },
502
- "+:model\\.layers\\.24\\.self_attn\\.o_proj": {
503
- "weight_type": "int6",
504
- "has_dynamic_zp": true,
505
- "weight_scale_group_size": 128
506
- },
507
- "+:model\\.layers\\.25\\.mlp\\.gate_proj": {
508
- "weight_type": "int5",
509
- "has_dynamic_zp": true,
510
- "weight_scale_group_size": 128
511
- },
512
- "+:model\\.layers\\.2\\.self_attn\\.o_proj": {
513
- "weight_type": "int6",
514
- "has_dynamic_zp": true,
515
- "weight_scale_group_size": 128
516
- },
517
- "+:model\\.layers\\.2\\.mlp\\.down_proj": {
518
- "weight_type": "int5",
519
- "has_dynamic_zp": true,
520
- "weight_scale_group_size": 128
521
- },
522
- "+:model\\.layers\\.16\\.self_attn\\.o_proj": {
523
- "weight_type": "int6",
524
- "has_dynamic_zp": true,
525
- "weight_scale_group_size": 128
526
- },
527
- "+:model\\.layers\\.18\\.mlp\\.gate_proj": {
528
- "weight_type": "int5",
529
- "has_dynamic_zp": true,
530
- "weight_scale_group_size": 128
531
- },
532
- "+:model\\.layers\\.6\\.self_attn\\.q_proj": {
533
- "weight_type": "int6",
534
- "has_dynamic_zp": true,
535
- "weight_scale_group_size": 128
536
- },
537
- "+:model\\.layers\\.28\\.mlp\\.down_proj": {
538
- "weight_type": "int5",
539
- "has_dynamic_zp": true,
540
- "weight_scale_group_size": 128
541
- },
542
- "+:model\\.layers\\.28\\.self_attn\\.o_proj": {
543
- "weight_type": "int6",
544
- "has_dynamic_zp": true,
545
- "weight_scale_group_size": 128
546
- },
547
- "+:model\\.layers\\.20\\.self_attn\\.q_proj": {
548
- "weight_type": "int7",
549
- "has_dynamic_zp": true,
550
- "weight_scale_group_size": 128
551
- },
552
- "+:model\\.layers\\.14\\.mlp\\.down_proj": {
553
- "weight_type": "int5",
554
- "has_dynamic_zp": true,
555
- "weight_scale_group_size": 128
556
- },
557
- "+:model\\.layers\\.35\\.self_attn\\.q_proj": {
558
- "weight_type": "int7",
559
- "has_dynamic_zp": true,
560
- "weight_scale_group_size": 128
561
- },
562
- "+:model\\.layers\\.30\\.mlp\\.gate_proj": {
563
- "weight_type": "int5",
564
- "has_dynamic_zp": true,
565
- "weight_scale_group_size": 128
566
- },
567
- "+:model\\.layers\\.24\\.mlp\\.gate_proj": {
568
- "weight_type": "int5",
569
- "has_dynamic_zp": true,
570
- "weight_scale_group_size": 128
571
- },
572
- "+:model\\.layers\\.14\\.mlp\\.up_proj": {
573
- "weight_type": "int6",
574
- "has_dynamic_zp": true,
575
- "weight_scale_group_size": 128
576
- },
577
- "+:model\\.layers\\.7\\.self_attn\\.q_proj": {
578
- "weight_type": "int7",
579
- "has_dynamic_zp": true,
580
- "weight_scale_group_size": 128
581
- },
582
- "+:model\\.layers\\.29\\.self_attn\\.o_proj": {
583
- "weight_type": "int6",
584
- "has_dynamic_zp": true,
585
- "weight_scale_group_size": 128
586
- },
587
- "+:model\\.layers\\.7\\.mlp\\.down_proj": {
588
- "weight_type": "int5",
589
- "has_dynamic_zp": true,
590
- "weight_scale_group_size": 128
591
- },
592
- "+:model\\.layers\\.17\\.self_attn\\.o_proj": {
593
- "weight_type": "int6",
594
- "has_dynamic_zp": true,
595
- "weight_scale_group_size": 128
596
- },
597
- "+:model\\.layers\\.34\\.mlp\\.up_proj": {
598
- "weight_type": "int6",
599
- "has_dynamic_zp": true,
600
- "weight_scale_group_size": 128
601
- },
602
- "+:model\\.layers\\.21\\.mlp\\.gate_proj": {
603
- "weight_type": "int5",
604
- "has_dynamic_zp": true,
605
- "weight_scale_group_size": 128
606
- },
607
- "+:model\\.layers\\.24\\.mlp\\.up_proj": {
608
- "weight_type": "int5",
609
- "has_dynamic_zp": true,
610
- "weight_scale_group_size": 128
611
- },
612
- "+:model\\.layers\\.8\\.mlp\\.up_proj": {
613
- "weight_type": "int5",
614
- "has_dynamic_zp": true,
615
- "weight_scale_group_size": 128
616
- },
617
- "+:model\\.layers\\.11\\.mlp\\.down_proj": {
618
- "weight_type": "int5",
619
- "has_dynamic_zp": true,
620
- "weight_scale_group_size": 128
621
- },
622
- "+:model\\.layers\\.7\\.mlp\\.up_proj": {
623
- "weight_type": "int5",
624
- "has_dynamic_zp": true,
625
- "weight_scale_group_size": 128
626
- },
627
- "+:model\\.layers\\.35\\.mlp\\.gate_proj": {
628
- "weight_type": "int7",
629
- "has_dynamic_zp": true,
630
- "weight_scale_group_size": 128
631
- },
632
- "+:model\\.layers\\.4\\.mlp\\.gate_proj": {
633
- "weight_type": "int5",
634
- "has_dynamic_zp": true,
635
- "weight_scale_group_size": 128
636
- },
637
- "+:model\\.layers\\.16\\.mlp\\.up_proj": {
638
- "weight_type": "int5",
639
- "has_dynamic_zp": true,
640
- "weight_scale_group_size": 128
641
- },
642
- "+:model\\.layers\\.19\\.mlp\\.up_proj": {
643
- "weight_type": "int5",
644
- "has_dynamic_zp": true,
645
- "weight_scale_group_size": 128
646
- },
647
- "+:model\\.layers\\.8\\.mlp\\.down_proj": {
648
- "weight_type": "int5",
649
- "has_dynamic_zp": true,
650
- "weight_scale_group_size": 128
651
- },
652
- "+:model\\.layers\\.12\\.mlp\\.gate_proj": {
653
- "weight_type": "int6",
654
- "has_dynamic_zp": true,
655
- "weight_scale_group_size": 128
656
- },
657
- "+:model\\.layers\\.14\\.self_attn\\.o_proj": {
658
- "weight_type": "int6",
659
- "has_dynamic_zp": true,
660
- "weight_scale_group_size": 128
661
- },
662
- "+:model\\.layers\\.22\\.mlp\\.down_proj": {
663
- "weight_type": "int5",
664
- "has_dynamic_zp": true,
665
- "weight_scale_group_size": 128
666
- },
667
- "+:model\\.layers\\.4\\.self_attn\\.q_proj": {
668
- "weight_type": "int6",
669
- "has_dynamic_zp": true,
670
- "weight_scale_group_size": 128
671
- },
672
- "+:model\\.layers\\.26\\.mlp\\.up_proj": {
673
- "weight_type": "int5",
674
- "has_dynamic_zp": true,
675
- "weight_scale_group_size": 128
676
- },
677
- "+:model\\.layers\\.29\\.mlp\\.up_proj": {
678
- "weight_type": "int5",
679
- "has_dynamic_zp": true,
680
- "weight_scale_group_size": 128
681
- },
682
- "+:model\\.layers\\.5\\.mlp\\.up_proj": {
683
- "weight_type": "int5",
684
- "has_dynamic_zp": true,
685
- "weight_scale_group_size": 128
686
- },
687
- "+:model\\.layers\\.1\\.mlp\\.gate_proj": {
688
- "weight_type": "int4",
689
- "has_dynamic_zp": true,
690
- "weight_scale_group_size": 128
691
- },
692
- "+:model\\.layers\\.27\\.mlp\\.down_proj": {
693
- "weight_type": "int5",
694
- "has_dynamic_zp": true,
695
- "weight_scale_group_size": 128
696
- },
697
- "+:model\\.layers\\.23\\.self_attn\\.q_proj": {
698
- "weight_type": "int7",
699
- "has_dynamic_zp": true,
700
- "weight_scale_group_size": 128
701
- },
702
- "+:model\\.layers\\.5\\.self_attn\\.q_proj": {
703
- "weight_type": "int6",
704
- "has_dynamic_zp": true,
705
- "weight_scale_group_size": 128
706
- },
707
- "+:model\\.layers\\.33\\.mlp\\.down_proj": {
708
- "weight_type": "int5",
709
- "has_dynamic_zp": true,
710
- "weight_scale_group_size": 128
711
- },
712
- "+:model\\.layers\\.17\\.mlp\\.gate_proj": {
713
- "weight_type": "int5",
714
- "has_dynamic_zp": true,
715
- "weight_scale_group_size": 128
716
- },
717
- "+:model\\.layers\\.15\\.self_attn\\.o_proj": {
718
- "weight_type": "int6",
719
- "has_dynamic_zp": true,
720
- "weight_scale_group_size": 128
721
- },
722
- "+:model\\.layers\\.13\\.self_attn\\.o_proj": {
723
- "weight_type": "int6",
724
- "has_dynamic_zp": true,
725
- "weight_scale_group_size": 128
726
- },
727
- "+:model\\.layers\\.29\\.mlp\\.gate_proj": {
728
- "weight_type": "int5",
729
- "has_dynamic_zp": true,
730
- "weight_scale_group_size": 128
731
- },
732
- "+:model\\.layers\\.25\\.self_attn\\.q_proj": {
733
- "weight_type": "int7",
734
- "has_dynamic_zp": true,
735
- "weight_scale_group_size": 128
736
- },
737
- "+:model\\.layers\\.30\\.mlp\\.up_proj": {
738
- "weight_type": "int5",
739
- "has_dynamic_zp": true,
740
- "weight_scale_group_size": 128
741
- },
742
- "+:model\\.layers\\.3\\.mlp\\.gate_proj": {
743
- "weight_type": "int4",
744
- "has_dynamic_zp": true,
745
- "weight_scale_group_size": 128
746
- },
747
- "+:model\\.layers\\.19\\.mlp\\.down_proj": {
748
- "weight_type": "int5",
749
- "has_dynamic_zp": true,
750
- "weight_scale_group_size": 128
751
- },
752
- "+:model\\.layers\\.3\\.self_attn\\.q_proj": {
753
- "weight_type": "int6",
754
- "has_dynamic_zp": true,
755
- "weight_scale_group_size": 128
756
- },
757
- "+:model\\.layers\\.20\\.mlp\\.up_proj": {
758
- "weight_type": "int5",
759
- "has_dynamic_zp": true,
760
- "weight_scale_group_size": 128
761
- },
762
- "+:model\\.layers\\.30\\.self_attn\\.q_proj": {
763
- "weight_type": "int7",
764
- "has_dynamic_zp": true,
765
- "weight_scale_group_size": 128
766
- },
767
- "+:model\\.layers\\.25\\.mlp\\.down_proj": {
768
- "weight_type": "int5",
769
- "has_dynamic_zp": true,
770
- "weight_scale_group_size": 128
771
- },
772
- "+:model\\.layers\\.3\\.mlp\\.up_proj": {
773
- "weight_type": "int4",
774
- "has_dynamic_zp": true,
775
- "weight_scale_group_size": 128
776
- },
777
- "+:model\\.layers\\.31\\.mlp\\.down_proj": {
778
- "weight_type": "int5",
779
- "has_dynamic_zp": true,
780
- "weight_scale_group_size": 128
781
- },
782
- "+:model\\.layers\\.15\\.mlp\\.gate_proj": {
783
- "weight_type": "int5",
784
- "has_dynamic_zp": true,
785
- "weight_scale_group_size": 128
786
- },
787
- "+:model\\.layers\\.2\\.self_attn\\.q_proj": {
788
- "weight_type": "int6",
789
- "has_dynamic_zp": true,
790
- "weight_scale_group_size": 128
791
- },
792
- "+:model\\.layers\\.6\\.mlp\\.gate_proj": {
793
- "weight_type": "int6",
794
- "has_dynamic_zp": true,
795
- "weight_scale_group_size": 128
796
- },
797
- "+:model\\.layers\\.12\\.self_attn\\.o_proj": {
798
- "weight_type": "int6",
799
- "has_dynamic_zp": true,
800
- "weight_scale_group_size": 128
801
- },
802
- "+:model\\.layers\\.34\\.mlp\\.down_proj": {
803
- "weight_type": "int5",
804
- "has_dynamic_zp": true,
805
- "weight_scale_group_size": 128
806
- },
807
- "+:model\\.layers\\.10\\.mlp\\.gate_proj": {
808
- "weight_type": "int6",
809
- "has_dynamic_zp": true,
810
- "weight_scale_group_size": 128
811
- },
812
- "+:model\\.layers\\.10\\.mlp\\.up_proj": {
813
- "weight_type": "int6",
814
- "has_dynamic_zp": true,
815
- "weight_scale_group_size": 128
816
- },
817
- "+:model\\.layers\\.20\\.mlp\\.down_proj": {
818
- "weight_type": "int5",
819
- "has_dynamic_zp": true,
820
- "weight_scale_group_size": 128
821
- },
822
- "+:model\\.layers\\.31\\.self_attn\\.q_proj": {
823
- "weight_type": "int7",
824
- "has_dynamic_zp": true,
825
- "weight_scale_group_size": 128
826
- },
827
- "+:model\\.layers\\.22\\.mlp\\.up_proj": {
828
- "weight_type": "int5",
829
- "has_dynamic_zp": true,
830
- "weight_scale_group_size": 128
831
- },
832
- "+:model\\.layers\\.5\\.mlp\\.down_proj": {
833
- "weight_type": "int5",
834
- "has_dynamic_zp": true,
835
- "weight_scale_group_size": 128
836
- },
837
- "+:model\\.layers\\.1\\.mlp\\.up_proj": {
838
- "weight_type": "int4",
839
- "has_dynamic_zp": true,
840
- "weight_scale_group_size": 128
841
- },
842
- "+:model\\.layers\\.11\\.self_attn\\.o_proj": {
843
- "weight_type": "int6",
844
- "has_dynamic_zp": true,
845
- "weight_scale_group_size": 128
846
- },
847
- "+:model\\.layers\\.23\\.mlp\\.gate_proj": {
848
- "weight_type": "int5",
849
- "has_dynamic_zp": true,
850
- "weight_scale_group_size": 128
851
- },
852
- "+:model\\.layers\\.32\\.mlp\\.up_proj": {
853
- "weight_type": "int6",
854
- "has_dynamic_zp": true,
855
- "weight_scale_group_size": 128
856
- },
857
- "+:model\\.layers\\.1\\.self_attn\\.q_proj": {
858
- "weight_type": "int6",
859
- "has_dynamic_zp": true,
860
- "weight_scale_group_size": 128
861
- },
862
- "+:model\\.layers\\.9\\.self_attn\\.o_proj": {
863
- "weight_type": "int6",
864
- "has_dynamic_zp": true,
865
- "weight_scale_group_size": 128
866
- },
867
- "+:model\\.layers\\.9\\.mlp\\.gate_proj": {
868
- "weight_type": "int6",
869
- "has_dynamic_zp": true,
870
- "weight_scale_group_size": 128
871
- },
872
- "+:model\\.layers\\.13\\.mlp\\.down_proj": {
873
- "weight_type": "int5",
874
- "has_dynamic_zp": true,
875
- "weight_scale_group_size": 128
876
- },
877
- "+:model\\.layers\\.0\\.mlp\\.down_proj": {
878
- "weight_type": "int5",
879
- "has_dynamic_zp": true,
880
- "weight_scale_group_size": 128
881
- },
882
- "+:model\\.layers\\.33\\.self_attn\\.q_proj": {
883
- "weight_type": "int7",
884
- "has_dynamic_zp": true,
885
- "weight_scale_group_size": 128
886
- },
887
- "+:model\\.layers\\.12\\.mlp\\.up_proj": {
888
- "weight_type": "int6",
889
- "has_dynamic_zp": true,
890
- "weight_scale_group_size": 128
891
- },
892
- "+:model\\.layers\\.8\\.self_attn\\.o_proj": {
893
- "weight_type": "int6",
894
- "has_dynamic_zp": true,
895
- "weight_scale_group_size": 128
896
- },
897
- "+:model\\.layers\\.0\\.self_attn\\.q_proj": {
898
- "weight_type": "int6",
899
- "has_dynamic_zp": true,
900
- "weight_scale_group_size": 128
901
- },
902
- "+:model\\.layers\\.16\\.mlp\\.down_proj": {
903
- "weight_type": "int5",
904
- "has_dynamic_zp": true,
905
- "weight_scale_group_size": 128
906
- },
907
- "+:model\\.layers\\.32\\.mlp\\.gate_proj": {
908
- "weight_type": "int6",
909
- "has_dynamic_zp": true,
910
- "weight_scale_group_size": 128
911
- },
912
- "+:model\\.layers\\.18\\.self_attn\\.q_proj": {
913
- "weight_type": "int7",
914
- "has_dynamic_zp": true,
915
- "weight_scale_group_size": 128
916
- },
917
- "+:model\\.layers\\.10\\.self_attn\\.o_proj": {
918
- "weight_type": "int6",
919
- "has_dynamic_zp": true,
920
- "weight_scale_group_size": 128
921
- },
922
- "+:model\\.layers\\.26\\.mlp\\.gate_proj": {
923
- "weight_type": "int5",
924
- "has_dynamic_zp": true,
925
- "weight_scale_group_size": 128
926
- }
927
- }
928
- }
929
- }
 
64
  "transformers_version": "4.57.3",
65
  "use_cache": false,
66
  "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/humming_online_quant_config.json ADDED
@@ -0,0 +1,517 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quant_method": "gptq",
3
+ "bits": 8,
4
+ "group_size": 128,
5
+ "dynamic": {
6
+ "+:model\\.layers\\.22\\.self_attn\\.o_proj": {
7
+ "bits": 6
8
+ },
9
+ "+:model\\.layers\\.4\\.self_attn\\.o_proj": {
10
+ "bits": 6
11
+ },
12
+ "+:model\\.layers\\.1\\.mlp\\.down_proj": {
13
+ "bits": 4
14
+ },
15
+ "+:model\\.layers\\.11\\.mlp\\.up_proj": {
16
+ "bits": 6
17
+ },
18
+ "+:model\\.layers\\.14\\.self_attn\\.q_proj": {
19
+ "bits": 7
20
+ },
21
+ "+:model\\.layers\\.17\\.mlp\\.down_proj": {
22
+ "bits": 5
23
+ },
24
+ "+:model\\.layers\\.33\\.mlp\\.gate_proj": {
25
+ "bits": 5
26
+ },
27
+ "+:model\\.layers\\.27\\.mlp\\.gate_proj": {
28
+ "bits": 6
29
+ },
30
+ "+:model\\.layers\\.2\\.mlp\\.up_proj": {
31
+ "bits": 5
32
+ },
33
+ "+:model\\.layers\\.15\\.self_attn\\.q_proj": {
34
+ "bits": 7
35
+ },
36
+ "+:model\\.layers\\.23\\.self_attn\\.o_proj": {
37
+ "bits": 7
38
+ },
39
+ "+:model\\.layers\\.21\\.mlp\\.up_proj": {
40
+ "bits": 5
41
+ },
42
+ "+:model\\.layers\\.4\\.mlp\\.down_proj": {
43
+ "bits": 5
44
+ },
45
+ "+:model\\.layers\\.5\\.self_attn\\.o_proj": {
46
+ "bits": 6
47
+ },
48
+ "+:model\\.layers\\.31\\.mlp\\.up_proj": {
49
+ "bits": 5
50
+ },
51
+ "+:model\\.layers\\.22\\.mlp\\.gate_proj": {
52
+ "bits": 5
53
+ },
54
+ "+:model\\.layers\\.8\\.mlp\\.gate_proj": {
55
+ "bits": 5
56
+ },
57
+ "+:model\\.layers\\.12\\.mlp\\.down_proj": {
58
+ "bits": 5
59
+ },
60
+ "+:model\\.layers\\.7\\.mlp\\.gate_proj": {
61
+ "bits": 5
62
+ },
63
+ "+:model\\.layers\\.35\\.self_attn\\.o_proj": {
64
+ "bits": 6
65
+ },
66
+ "+:model\\.layers\\.6\\.self_attn\\.o_proj": {
67
+ "bits": 6
68
+ },
69
+ "+:model\\.layers\\.20\\.self_attn\\.o_proj": {
70
+ "bits": 6
71
+ },
72
+ "+:model\\.layers\\.13\\.mlp\\.up_proj": {
73
+ "bits": 6
74
+ },
75
+ "+:model\\.layers\\.35\\.mlp\\.down_proj": {
76
+ "bits": 6
77
+ },
78
+ "+:model\\.layers\\.11\\.mlp\\.gate_proj": {
79
+ "bits": 6
80
+ },
81
+ "+:model\\.layers\\.21\\.mlp\\.down_proj": {
82
+ "bits": 5
83
+ },
84
+ "+:model\\.layers\\.33\\.mlp\\.up_proj": {
85
+ "bits": 5
86
+ },
87
+ "+:model\\.layers\\.34\\.self_attn\\.o_proj": {
88
+ "bits": 6
89
+ },
90
+ "+:model\\.layers\\.28\\.mlp\\.gate_proj": {
91
+ "bits": 5
92
+ },
93
+ "+:model\\.layers\\.2\\.mlp\\.gate_proj": {
94
+ "bits": 5
95
+ },
96
+ "+:model\\.layers\\.18\\.mlp\\.down_proj": {
97
+ "bits": 5
98
+ },
99
+ "+:model\\.layers\\.17\\.self_attn\\.q_proj": {
100
+ "bits": 7
101
+ },
102
+ "+:model\\.layers\\.0\\.mlp\\.up_proj": {
103
+ "bits": 4
104
+ },
105
+ "+:model\\.layers\\.24\\.mlp\\.down_proj": {
106
+ "bits": 5
107
+ },
108
+ "+:model\\.layers\\.23\\.mlp\\.up_proj": {
109
+ "bits": 5
110
+ },
111
+ "+:model\\.layers\\.7\\.self_attn\\.o_proj": {
112
+ "bits": 6
113
+ },
114
+ "+:model\\.layers\\.29\\.self_attn\\.q_proj": {
115
+ "bits": 7
116
+ },
117
+ "+:model\\.layers\\.30\\.mlp\\.down_proj": {
118
+ "bits": 5
119
+ },
120
+ "+:model\\.layers\\.14\\.mlp\\.gate_proj": {
121
+ "bits": 6
122
+ },
123
+ "+:model\\.layers\\.21\\.self_attn\\.o_proj": {
124
+ "bits": 6
125
+ },
126
+ "+:model\\.layers\\.6\\.mlp\\.up_proj": {
127
+ "bits": 6
128
+ },
129
+ "+:model\\.layers\\.9\\.self_attn\\.q_proj": {
130
+ "bits": 7
131
+ },
132
+ "+:model\\.layers\\.9\\.mlp\\.up_proj": {
133
+ "bits": 6
134
+ },
135
+ "+:model\\.layers\\.1\\.self_attn\\.o_proj": {
136
+ "bits": 6
137
+ },
138
+ "+:model\\.layers\\.27\\.self_attn\\.o_proj": {
139
+ "bits": 6
140
+ },
141
+ "+:model\\.layers\\.19\\.self_attn\\.o_proj": {
142
+ "bits": 6
143
+ },
144
+ "+:model\\.layers\\.0\\.mlp\\.gate_proj": {
145
+ "bits": 4
146
+ },
147
+ "+:model\\.layers\\.11\\.self_attn\\.q_proj": {
148
+ "bits": 7
149
+ },
150
+ "+:model\\.layers\\.25\\.mlp\\.up_proj": {
151
+ "bits": 5
152
+ },
153
+ "+:model\\.layers\\.26\\.mlp\\.down_proj": {
154
+ "bits": 5
155
+ },
156
+ "+:model\\.layers\\.35\\.mlp\\.up_proj": {
157
+ "bits": 7
158
+ },
159
+ "+:model\\.layers\\.32\\.self_attn\\.o_proj": {
160
+ "bits": 6
161
+ },
162
+ "+:model\\.layers\\.32\\.mlp\\.down_proj": {
163
+ "bits": 5
164
+ },
165
+ "+:model\\.layers\\.16\\.mlp\\.gate_proj": {
166
+ "bits": 5
167
+ },
168
+ "+:model\\.layers\\.15\\.mlp\\.up_proj": {
169
+ "bits": 5
170
+ },
171
+ "+:model\\.layers\\.10\\.self_attn\\.q_proj": {
172
+ "bits": 7
173
+ },
174
+ "+:model\\.layers\\.5\\.mlp\\.gate_proj": {
175
+ "bits": 5
176
+ },
177
+ "+:model\\.layers\\.18\\.self_attn\\.o_proj": {
178
+ "bits": 6
179
+ },
180
+ "+:model\\.layers\\.0\\.self_attn\\.o_proj": {
181
+ "bits": 6
182
+ },
183
+ "+:model\\.layers\\.8\\.self_attn\\.q_proj": {
184
+ "bits": 7
185
+ },
186
+ "+:model\\.layers\\.26\\.self_attn\\.o_proj": {
187
+ "bits": 6
188
+ },
189
+ "+:model\\.layers\\.9\\.mlp\\.down_proj": {
190
+ "bits": 5
191
+ },
192
+ "+:model\\.layers\\.13\\.mlp\\.gate_proj": {
193
+ "bits": 6
194
+ },
195
+ "+:model\\.layers\\.33\\.self_attn\\.o_proj": {
196
+ "bits": 6
197
+ },
198
+ "+:model\\.layers\\.23\\.mlp\\.down_proj": {
199
+ "bits": 5
200
+ },
201
+ "+:model\\.layers\\.6\\.mlp\\.down_proj": {
202
+ "bits": 6
203
+ },
204
+ "+:model\\.layers\\.30\\.self_attn\\.o_proj": {
205
+ "bits": 6
206
+ },
207
+ "+:model\\.layers\\.4\\.mlp\\.up_proj": {
208
+ "bits": 5
209
+ },
210
+ "+:model\\.layers\\.25\\.self_attn\\.o_proj": {
211
+ "bits": 6
212
+ },
213
+ "+:model\\.layers\\.20\\.mlp\\.gate_proj": {
214
+ "bits": 5
215
+ },
216
+ "+:model\\.layers\\.3\\.self_attn\\.o_proj": {
217
+ "bits": 6
218
+ },
219
+ "+:model\\.layers\\.10\\.mlp\\.down_proj": {
220
+ "bits": 6
221
+ },
222
+ "+:model\\.layers\\.34\\.mlp\\.gate_proj": {
223
+ "bits": 6
224
+ },
225
+ "+:model\\.layers\\.13\\.self_attn\\.q_proj": {
226
+ "bits": 7
227
+ },
228
+ "+:model\\.layers\\.28\\.mlp\\.up_proj": {
229
+ "bits": 5
230
+ },
231
+ "+:model\\.layers\\.27\\.mlp\\.up_proj": {
232
+ "bits": 6
233
+ },
234
+ "+:model\\.layers\\.3\\.mlp\\.down_proj": {
235
+ "bits": 5
236
+ },
237
+ "+:model\\.layers\\.19\\.mlp\\.gate_proj": {
238
+ "bits": 5
239
+ },
240
+ "+:model\\.layers\\.31\\.self_attn\\.o_proj": {
241
+ "bits": 6
242
+ },
243
+ "+:model\\.layers\\.29\\.mlp\\.down_proj": {
244
+ "bits": 5
245
+ },
246
+ "+:model\\.layers\\.18\\.mlp\\.up_proj": {
247
+ "bits": 5
248
+ },
249
+ "+:model\\.layers\\.15\\.mlp\\.down_proj": {
250
+ "bits": 5
251
+ },
252
+ "+:model\\.layers\\.17\\.mlp\\.up_proj": {
253
+ "bits": 5
254
+ },
255
+ "+:model\\.layers\\.31\\.mlp\\.gate_proj": {
256
+ "bits": 5
257
+ },
258
+ "+:model\\.layers\\.12\\.self_attn\\.q_proj": {
259
+ "bits": 7
260
+ },
261
+ "+:model\\.layers\\.24\\.self_attn\\.o_proj": {
262
+ "bits": 6
263
+ },
264
+ "+:model\\.layers\\.25\\.mlp\\.gate_proj": {
265
+ "bits": 5
266
+ },
267
+ "+:model\\.layers\\.2\\.self_attn\\.o_proj": {
268
+ "bits": 6
269
+ },
270
+ "+:model\\.layers\\.2\\.mlp\\.down_proj": {
271
+ "bits": 5
272
+ },
273
+ "+:model\\.layers\\.16\\.self_attn\\.o_proj": {
274
+ "bits": 6
275
+ },
276
+ "+:model\\.layers\\.18\\.mlp\\.gate_proj": {
277
+ "bits": 5
278
+ },
279
+ "+:model\\.layers\\.6\\.self_attn\\.q_proj": {
280
+ "bits": 6
281
+ },
282
+ "+:model\\.layers\\.28\\.mlp\\.down_proj": {
283
+ "bits": 5
284
+ },
285
+ "+:model\\.layers\\.28\\.self_attn\\.o_proj": {
286
+ "bits": 6
287
+ },
288
+ "+:model\\.layers\\.20\\.self_attn\\.q_proj": {
289
+ "bits": 7
290
+ },
291
+ "+:model\\.layers\\.14\\.mlp\\.down_proj": {
292
+ "bits": 5
293
+ },
294
+ "+:model\\.layers\\.35\\.self_attn\\.q_proj": {
295
+ "bits": 7
296
+ },
297
+ "+:model\\.layers\\.30\\.mlp\\.gate_proj": {
298
+ "bits": 5
299
+ },
300
+ "+:model\\.layers\\.24\\.mlp\\.gate_proj": {
301
+ "bits": 5
302
+ },
303
+ "+:model\\.layers\\.14\\.mlp\\.up_proj": {
304
+ "bits": 6
305
+ },
306
+ "+:model\\.layers\\.7\\.self_attn\\.q_proj": {
307
+ "bits": 7
308
+ },
309
+ "+:model\\.layers\\.29\\.self_attn\\.o_proj": {
310
+ "bits": 6
311
+ },
312
+ "+:model\\.layers\\.7\\.mlp\\.down_proj": {
313
+ "bits": 5
314
+ },
315
+ "+:model\\.layers\\.17\\.self_attn\\.o_proj": {
316
+ "bits": 6
317
+ },
318
+ "+:model\\.layers\\.34\\.mlp\\.up_proj": {
319
+ "bits": 6
320
+ },
321
+ "+:model\\.layers\\.21\\.mlp\\.gate_proj": {
322
+ "bits": 5
323
+ },
324
+ "+:model\\.layers\\.24\\.mlp\\.up_proj": {
325
+ "bits": 5
326
+ },
327
+ "+:model\\.layers\\.8\\.mlp\\.up_proj": {
328
+ "bits": 5
329
+ },
330
+ "+:model\\.layers\\.11\\.mlp\\.down_proj": {
331
+ "bits": 5
332
+ },
333
+ "+:model\\.layers\\.7\\.mlp\\.up_proj": {
334
+ "bits": 5
335
+ },
336
+ "+:model\\.layers\\.35\\.mlp\\.gate_proj": {
337
+ "bits": 7
338
+ },
339
+ "+:model\\.layers\\.4\\.mlp\\.gate_proj": {
340
+ "bits": 5
341
+ },
342
+ "+:model\\.layers\\.16\\.mlp\\.up_proj": {
343
+ "bits": 5
344
+ },
345
+ "+:model\\.layers\\.19\\.mlp\\.up_proj": {
346
+ "bits": 5
347
+ },
348
+ "+:model\\.layers\\.8\\.mlp\\.down_proj": {
349
+ "bits": 5
350
+ },
351
+ "+:model\\.layers\\.12\\.mlp\\.gate_proj": {
352
+ "bits": 6
353
+ },
354
+ "+:model\\.layers\\.14\\.self_attn\\.o_proj": {
355
+ "bits": 6
356
+ },
357
+ "+:model\\.layers\\.22\\.mlp\\.down_proj": {
358
+ "bits": 5
359
+ },
360
+ "+:model\\.layers\\.4\\.self_attn\\.q_proj": {
361
+ "bits": 6
362
+ },
363
+ "+:model\\.layers\\.26\\.mlp\\.up_proj": {
364
+ "bits": 5
365
+ },
366
+ "+:model\\.layers\\.29\\.mlp\\.up_proj": {
367
+ "bits": 5
368
+ },
369
+ "+:model\\.layers\\.5\\.mlp\\.up_proj": {
370
+ "bits": 5
371
+ },
372
+ "+:model\\.layers\\.1\\.mlp\\.gate_proj": {
373
+ "bits": 4
374
+ },
375
+ "+:model\\.layers\\.27\\.mlp\\.down_proj": {
376
+ "bits": 5
377
+ },
378
+ "+:model\\.layers\\.23\\.self_attn\\.q_proj": {
379
+ "bits": 7
380
+ },
381
+ "+:model\\.layers\\.5\\.self_attn\\.q_proj": {
382
+ "bits": 6
383
+ },
384
+ "+:model\\.layers\\.33\\.mlp\\.down_proj": {
385
+ "bits": 5
386
+ },
387
+ "+:model\\.layers\\.17\\.mlp\\.gate_proj": {
388
+ "bits": 5
389
+ },
390
+ "+:model\\.layers\\.15\\.self_attn\\.o_proj": {
391
+ "bits": 6
392
+ },
393
+ "+:model\\.layers\\.13\\.self_attn\\.o_proj": {
394
+ "bits": 6
395
+ },
396
+ "+:model\\.layers\\.29\\.mlp\\.gate_proj": {
397
+ "bits": 5
398
+ },
399
+ "+:model\\.layers\\.25\\.self_attn\\.q_proj": {
400
+ "bits": 7
401
+ },
402
+ "+:model\\.layers\\.30\\.mlp\\.up_proj": {
403
+ "bits": 5
404
+ },
405
+ "+:model\\.layers\\.3\\.mlp\\.gate_proj": {
406
+ "bits": 4
407
+ },
408
+ "+:model\\.layers\\.19\\.mlp\\.down_proj": {
409
+ "bits": 5
410
+ },
411
+ "+:model\\.layers\\.3\\.self_attn\\.q_proj": {
412
+ "bits": 6
413
+ },
414
+ "+:model\\.layers\\.20\\.mlp\\.up_proj": {
415
+ "bits": 5
416
+ },
417
+ "+:model\\.layers\\.30\\.self_attn\\.q_proj": {
418
+ "bits": 7
419
+ },
420
+ "+:model\\.layers\\.25\\.mlp\\.down_proj": {
421
+ "bits": 5
422
+ },
423
+ "+:model\\.layers\\.3\\.mlp\\.up_proj": {
424
+ "bits": 4
425
+ },
426
+ "+:model\\.layers\\.31\\.mlp\\.down_proj": {
427
+ "bits": 5
428
+ },
429
+ "+:model\\.layers\\.15\\.mlp\\.gate_proj": {
430
+ "bits": 5
431
+ },
432
+ "+:model\\.layers\\.2\\.self_attn\\.q_proj": {
433
+ "bits": 6
434
+ },
435
+ "+:model\\.layers\\.6\\.mlp\\.gate_proj": {
436
+ "bits": 6
437
+ },
438
+ "+:model\\.layers\\.12\\.self_attn\\.o_proj": {
439
+ "bits": 6
440
+ },
441
+ "+:model\\.layers\\.34\\.mlp\\.down_proj": {
442
+ "bits": 5
443
+ },
444
+ "+:model\\.layers\\.10\\.mlp\\.gate_proj": {
445
+ "bits": 6
446
+ },
447
+ "+:model\\.layers\\.10\\.mlp\\.up_proj": {
448
+ "bits": 6
449
+ },
450
+ "+:model\\.layers\\.20\\.mlp\\.down_proj": {
451
+ "bits": 5
452
+ },
453
+ "+:model\\.layers\\.31\\.self_attn\\.q_proj": {
454
+ "bits": 7
455
+ },
456
+ "+:model\\.layers\\.22\\.mlp\\.up_proj": {
457
+ "bits": 5
458
+ },
459
+ "+:model\\.layers\\.5\\.mlp\\.down_proj": {
460
+ "bits": 5
461
+ },
462
+ "+:model\\.layers\\.1\\.mlp\\.up_proj": {
463
+ "bits": 4
464
+ },
465
+ "+:model\\.layers\\.11\\.self_attn\\.o_proj": {
466
+ "bits": 6
467
+ },
468
+ "+:model\\.layers\\.23\\.mlp\\.gate_proj": {
469
+ "bits": 5
470
+ },
471
+ "+:model\\.layers\\.32\\.mlp\\.up_proj": {
472
+ "bits": 6
473
+ },
474
+ "+:model\\.layers\\.1\\.self_attn\\.q_proj": {
475
+ "bits": 6
476
+ },
477
+ "+:model\\.layers\\.9\\.self_attn\\.o_proj": {
478
+ "bits": 6
479
+ },
480
+ "+:model\\.layers\\.9\\.mlp\\.gate_proj": {
481
+ "bits": 6
482
+ },
483
+ "+:model\\.layers\\.13\\.mlp\\.down_proj": {
484
+ "bits": 5
485
+ },
486
+ "+:model\\.layers\\.0\\.mlp\\.down_proj": {
487
+ "bits": 5
488
+ },
489
+ "+:model\\.layers\\.33\\.self_attn\\.q_proj": {
490
+ "bits": 7
491
+ },
492
+ "+:model\\.layers\\.12\\.mlp\\.up_proj": {
493
+ "bits": 6
494
+ },
495
+ "+:model\\.layers\\.8\\.self_attn\\.o_proj": {
496
+ "bits": 6
497
+ },
498
+ "+:model\\.layers\\.0\\.self_attn\\.q_proj": {
499
+ "bits": 6
500
+ },
501
+ "+:model\\.layers\\.16\\.mlp\\.down_proj": {
502
+ "bits": 5
503
+ },
504
+ "+:model\\.layers\\.32\\.mlp\\.gate_proj": {
505
+ "bits": 6
506
+ },
507
+ "+:model\\.layers\\.18\\.self_attn\\.q_proj": {
508
+ "bits": 7
509
+ },
510
+ "+:model\\.layers\\.10\\.self_attn\\.o_proj": {
511
+ "bits": 6
512
+ },
513
+ "+:model\\.layers\\.26\\.mlp\\.gate_proj": {
514
+ "bits": 5
515
+ }
516
+ }
517
+ }
humming/Qwen3-8B/ll_sha_bw8.16_8bit/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12288,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 1000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": false,
64
+ "transformers_version": "4.57.3",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
humming/Qwen3-8B/ll_sha_bw8.16_8bit/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
humming/Qwen3-8B/ll_sha_bw8.16_8bit/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
humming/Qwen3-8B/ll_sha_bw8.16_8bit/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
humming/Qwen3-8B/ll_sha_bw8.16_8bit/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
humming/Qwen3-8B/ll_sha_bw8.16_8bit/vocab.json ADDED
The diff for this file is too large to render. See raw diff