Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/README.md +18 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/added_tokens.json +28 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/chat_template.jinja +89 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/config.json +929 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/generation_config.json +13 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/merges.txt +0 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model-00001-of-00004.safetensors +3 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model-00002-of-00004.safetensors +3 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model-00003-of-00004.safetensors +3 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model-00004-of-00004.safetensors +3 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model.safetensors.index.json +407 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/quantization_config.txt +281 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/special_tokens_map.json +25 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/tokenizer.json +3 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/tokenizer_config.json +239 -0
- humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -112,3 +112,4 @@ nvfp-acts/Qwen3-8B/ll_bsearch_kl0.01_eap0.95_sha_bw7.15_4-8bit_grouped_seed42/to
|
|
| 112 |
nvfp-acts/Qwen3-8B/ll_bsearch_kl0.005_eap0.95_sha_bw7.77_4-8bit_grouped_seed42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 113 |
nvfp-acts/Qwen3-8B/ll_bsearch_kl0.005_eap0.95_sha_bw7.81_4-8bit_grouped_seed1234/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 114 |
nvfp-acts/Qwen3-8B/ll_bsearch_kl0.01_eap0.95_sha_bw7.14_4-8bit_grouped_seed1234/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 112 |
nvfp-acts/Qwen3-8B/ll_bsearch_kl0.005_eap0.95_sha_bw7.77_4-8bit_grouped_seed42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 113 |
nvfp-acts/Qwen3-8B/ll_bsearch_kl0.005_eap0.95_sha_bw7.81_4-8bit_grouped_seed1234/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 114 |
nvfp-acts/Qwen3-8B/ll_bsearch_kl0.01_eap0.95_sha_bw7.14_4-8bit_grouped_seed1234/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Quantized Model Checkpoint
|
| 2 |
+
|
| 3 |
+
**Base model:** Qwen/Qwen3-8B
|
| 4 |
+
|
| 5 |
+
**Average bitwidth:** 5.7019
|
| 6 |
+
|
| 7 |
+
**Sensitivity method:** shapley
|
| 8 |
+
|
| 9 |
+
**Constraints:**
|
| 10 |
+
- max_kl: 0.005
|
| 11 |
+
- min_eap: 0.99
|
| 12 |
+
|
| 13 |
+
**Metrics:**
|
| 14 |
+
- final_kl: 0.002276
|
| 15 |
+
- final_eap: 0.990127
|
| 16 |
+
- final_etl: 0.009873
|
| 17 |
+
|
| 18 |
+
See `quantization_config.txt` for full configuration details.
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_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/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_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/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/config.json
ADDED
|
@@ -0,0 +1,929 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"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 |
+
}
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_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/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/merges.txt
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/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53774914f37d118e8cc6b076a90d06a244ecf85b6f6bdac60e63e4f6cf2ec5da
|
| 3 |
+
size 4902257592
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d41c38f1ef8a71a68ff9fff59bc826fc6fe6d27f8350aed0a4a81c89ecb3a233
|
| 3 |
+
size 4915960224
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1fa198f3b2e766fe285d5883fb6a8693aac5d9e56f9e62929ea67ee5ca0509
|
| 3 |
+
size 4983068360
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6bb6506870f1266fec7a3a9f33a6fa98ca17c1f643783e0fc70ce91833d2bc6
|
| 3 |
+
size 1580230248
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8190735360,
|
| 4 |
+
"total_size": 16381470720
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 185 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 339 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 406 |
+
}
|
| 407 |
+
}
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/quantization_config.txt
ADDED
|
@@ -0,0 +1,281 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model: Qwen/Qwen3-8B
|
| 2 |
+
# Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4_5_6_7_8bit_asym_g128/Qwen3-8B/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: 0.005
|
| 10 |
+
# Constraint min_eap: 0.99
|
| 11 |
+
# Weights: nll=0.0, kl=0.0, eap=1.0
|
| 12 |
+
#
|
| 13 |
+
# Average bitwidth: 5.7019
|
| 14 |
+
# Total params: 6945767424
|
| 15 |
+
# Total bits: 39604027654
|
| 16 |
+
# Final KL: 0.002276
|
| 17 |
+
# Final EAP: 0.990127
|
| 18 |
+
# Final ETL: 0.009873
|
| 19 |
+
# Satisfies constraints: True
|
| 20 |
+
# Solver calls: 9
|
| 21 |
+
# Evaluations: 9
|
| 22 |
+
#
|
| 23 |
+
# Bitwidth distribution:
|
| 24 |
+
# 8-bit: 82 layers (32.5%)
|
| 25 |
+
# 7-bit: 22 layers (8.7%)
|
| 26 |
+
# 6-bit: 65 layers (25.8%)
|
| 27 |
+
# 5-bit: 76 layers (30.2%)
|
| 28 |
+
# 4-bit: 7 layers (2.8%)
|
| 29 |
+
#
|
| 30 |
+
model.layers.23.self_attn.k_proj: 8
|
| 31 |
+
model.layers.22.self_attn.o_proj: 6
|
| 32 |
+
model.layers.4.self_attn.o_proj: 6
|
| 33 |
+
model.layers.1.mlp.down_proj: 4
|
| 34 |
+
model.layers.11.mlp.up_proj: 6
|
| 35 |
+
model.layers.5.self_attn.k_proj: 8
|
| 36 |
+
model.layers.14.self_attn.q_proj: 7
|
| 37 |
+
model.layers.17.mlp.down_proj: 5
|
| 38 |
+
model.layers.33.mlp.gate_proj: 5
|
| 39 |
+
model.layers.5.self_attn.v_proj: 8
|
| 40 |
+
model.layers.23.self_attn.v_proj: 8
|
| 41 |
+
model.layers.27.mlp.gate_proj: 6
|
| 42 |
+
model.layers.2.mlp.up_proj: 5
|
| 43 |
+
model.layers.15.self_attn.q_proj: 7
|
| 44 |
+
model.layers.23.self_attn.o_proj: 7
|
| 45 |
+
model.layers.21.mlp.up_proj: 5
|
| 46 |
+
model.layers.22.self_attn.k_proj: 8
|
| 47 |
+
model.layers.4.mlp.down_proj: 5
|
| 48 |
+
model.layers.4.self_attn.k_proj: 8
|
| 49 |
+
model.layers.5.self_attn.o_proj: 6
|
| 50 |
+
model.layers.31.mlp.up_proj: 5
|
| 51 |
+
model.layers.4.self_attn.v_proj: 8
|
| 52 |
+
model.layers.22.self_attn.v_proj: 8
|
| 53 |
+
model.layers.22.mlp.gate_proj: 5
|
| 54 |
+
model.layers.8.mlp.gate_proj: 5
|
| 55 |
+
model.layers.12.mlp.down_proj: 5
|
| 56 |
+
model.layers.7.mlp.gate_proj: 5
|
| 57 |
+
model.layers.35.self_attn.o_proj: 6
|
| 58 |
+
model.layers.21.self_attn.v_proj: 8
|
| 59 |
+
model.layers.34.self_attn.k_proj: 8
|
| 60 |
+
model.layers.7.self_attn.v_proj: 8
|
| 61 |
+
model.layers.7.self_attn.k_proj: 8
|
| 62 |
+
model.layers.6.self_attn.o_proj: 6
|
| 63 |
+
model.layers.34.self_attn.v_proj: 8
|
| 64 |
+
model.layers.20.self_attn.o_proj: 6
|
| 65 |
+
model.layers.13.mlp.up_proj: 6
|
| 66 |
+
model.layers.21.self_attn.k_proj: 8
|
| 67 |
+
model.layers.35.mlp.down_proj: 6
|
| 68 |
+
model.layers.28.self_attn.q_proj: 8
|
| 69 |
+
model.layers.11.mlp.gate_proj: 6
|
| 70 |
+
model.layers.16.self_attn.q_proj: 8
|
| 71 |
+
model.layers.21.mlp.down_proj: 5
|
| 72 |
+
model.layers.35.self_attn.k_proj: 8
|
| 73 |
+
model.layers.33.mlp.up_proj: 5
|
| 74 |
+
model.layers.20.self_attn.v_proj: 8
|
| 75 |
+
model.layers.34.self_attn.o_proj: 6
|
| 76 |
+
model.layers.6.self_attn.v_proj: 8
|
| 77 |
+
model.layers.28.mlp.gate_proj: 5
|
| 78 |
+
model.layers.2.mlp.gate_proj: 5
|
| 79 |
+
model.layers.18.mlp.down_proj: 5
|
| 80 |
+
model.layers.17.self_attn.q_proj: 7
|
| 81 |
+
model.layers.0.mlp.up_proj: 4
|
| 82 |
+
model.layers.24.mlp.down_proj: 5
|
| 83 |
+
model.layers.23.mlp.up_proj: 5
|
| 84 |
+
model.layers.7.self_attn.o_proj: 6
|
| 85 |
+
model.layers.6.self_attn.k_proj: 8
|
| 86 |
+
model.layers.29.self_attn.q_proj: 7
|
| 87 |
+
model.layers.20.self_attn.k_proj: 8
|
| 88 |
+
model.layers.30.mlp.down_proj: 5
|
| 89 |
+
model.layers.14.mlp.gate_proj: 6
|
| 90 |
+
model.layers.21.self_attn.o_proj: 6
|
| 91 |
+
model.layers.35.self_attn.v_proj: 8
|
| 92 |
+
model.layers.6.mlp.up_proj: 6
|
| 93 |
+
model.layers.9.self_attn.q_proj: 7
|
| 94 |
+
model.layers.0.self_attn.k_proj: 8
|
| 95 |
+
model.layers.9.mlp.up_proj: 6
|
| 96 |
+
model.layers.1.self_attn.o_proj: 6
|
| 97 |
+
model.layers.33.self_attn.v_proj: 8
|
| 98 |
+
model.layers.27.self_attn.o_proj: 6
|
| 99 |
+
model.layers.26.self_attn.k_proj: 8
|
| 100 |
+
model.layers.19.self_attn.o_proj: 6
|
| 101 |
+
model.layers.0.mlp.gate_proj: 4
|
| 102 |
+
model.layers.11.self_attn.q_proj: 7
|
| 103 |
+
model.layers.18.self_attn.k_proj: 8
|
| 104 |
+
model.layers.25.mlp.up_proj: 5
|
| 105 |
+
model.layers.26.mlp.down_proj: 5
|
| 106 |
+
model.layers.18.self_attn.v_proj: 8
|
| 107 |
+
model.layers.35.mlp.up_proj: 7
|
| 108 |
+
model.layers.32.self_attn.o_proj: 6
|
| 109 |
+
model.layers.26.self_attn.v_proj: 8
|
| 110 |
+
model.layers.33.self_attn.k_proj: 8
|
| 111 |
+
model.layers.32.mlp.down_proj: 5
|
| 112 |
+
model.layers.16.mlp.gate_proj: 5
|
| 113 |
+
model.layers.0.self_attn.v_proj: 8
|
| 114 |
+
model.layers.15.mlp.up_proj: 5
|
| 115 |
+
model.layers.19.self_attn.k_proj: 8
|
| 116 |
+
model.layers.10.self_attn.q_proj: 7
|
| 117 |
+
model.layers.5.mlp.gate_proj: 5
|
| 118 |
+
model.layers.18.self_attn.o_proj: 6
|
| 119 |
+
model.layers.0.self_attn.o_proj: 6
|
| 120 |
+
model.layers.1.self_attn.k_proj: 8
|
| 121 |
+
model.layers.8.self_attn.q_proj: 7
|
| 122 |
+
model.layers.27.self_attn.k_proj: 8
|
| 123 |
+
model.layers.26.self_attn.o_proj: 6
|
| 124 |
+
model.layers.32.self_attn.v_proj: 8
|
| 125 |
+
model.layers.9.mlp.down_proj: 5
|
| 126 |
+
model.layers.32.self_attn.k_proj: 8
|
| 127 |
+
model.layers.13.mlp.gate_proj: 6
|
| 128 |
+
model.layers.27.self_attn.v_proj: 8
|
| 129 |
+
model.layers.33.self_attn.o_proj: 6
|
| 130 |
+
model.layers.1.self_attn.v_proj: 8
|
| 131 |
+
model.layers.23.mlp.down_proj: 5
|
| 132 |
+
model.layers.19.self_attn.v_proj: 8
|
| 133 |
+
model.layers.2.self_attn.v_proj: 8
|
| 134 |
+
model.layers.6.mlp.down_proj: 6
|
| 135 |
+
model.layers.31.self_attn.k_proj: 8
|
| 136 |
+
model.layers.24.self_attn.v_proj: 8
|
| 137 |
+
model.layers.30.self_attn.o_proj: 6
|
| 138 |
+
model.layers.24.self_attn.k_proj: 8
|
| 139 |
+
model.layers.4.mlp.up_proj: 5
|
| 140 |
+
model.layers.25.self_attn.o_proj: 6
|
| 141 |
+
model.layers.31.self_attn.v_proj: 8
|
| 142 |
+
model.layers.20.mlp.gate_proj: 5
|
| 143 |
+
model.layers.3.self_attn.o_proj: 6
|
| 144 |
+
model.layers.2.self_attn.k_proj: 8
|
| 145 |
+
model.layers.10.mlp.down_proj: 6
|
| 146 |
+
model.layers.34.mlp.gate_proj: 6
|
| 147 |
+
model.layers.13.self_attn.q_proj: 7
|
| 148 |
+
model.layers.28.mlp.up_proj: 5
|
| 149 |
+
model.layers.27.mlp.up_proj: 6
|
| 150 |
+
model.layers.3.mlp.down_proj: 5
|
| 151 |
+
model.layers.3.self_attn.v_proj: 8
|
| 152 |
+
model.layers.19.mlp.gate_proj: 5
|
| 153 |
+
model.layers.31.self_attn.o_proj: 6
|
| 154 |
+
model.layers.25.self_attn.v_proj: 8
|
| 155 |
+
model.layers.30.self_attn.k_proj: 8
|
| 156 |
+
model.layers.29.mlp.down_proj: 5
|
| 157 |
+
model.layers.18.mlp.up_proj: 5
|
| 158 |
+
model.layers.15.mlp.down_proj: 5
|
| 159 |
+
model.layers.17.mlp.up_proj: 5
|
| 160 |
+
model.layers.31.mlp.gate_proj: 5
|
| 161 |
+
model.layers.12.self_attn.q_proj: 7
|
| 162 |
+
model.layers.30.self_attn.v_proj: 8
|
| 163 |
+
model.layers.24.self_attn.o_proj: 6
|
| 164 |
+
model.layers.25.self_attn.k_proj: 8
|
| 165 |
+
model.layers.25.mlp.gate_proj: 5
|
| 166 |
+
model.layers.3.self_attn.k_proj: 8
|
| 167 |
+
model.layers.2.self_attn.o_proj: 6
|
| 168 |
+
model.layers.2.mlp.down_proj: 5
|
| 169 |
+
model.layers.16.self_attn.o_proj: 6
|
| 170 |
+
model.layers.18.mlp.gate_proj: 5
|
| 171 |
+
model.layers.17.self_attn.k_proj: 8
|
| 172 |
+
model.layers.6.self_attn.q_proj: 6
|
| 173 |
+
model.layers.28.mlp.down_proj: 5
|
| 174 |
+
model.layers.28.self_attn.o_proj: 6
|
| 175 |
+
model.layers.20.self_attn.q_proj: 7
|
| 176 |
+
model.layers.29.self_attn.k_proj: 8
|
| 177 |
+
model.layers.29.self_attn.v_proj: 8
|
| 178 |
+
model.layers.14.mlp.down_proj: 5
|
| 179 |
+
model.layers.35.self_attn.q_proj: 7
|
| 180 |
+
model.layers.30.mlp.gate_proj: 5
|
| 181 |
+
model.layers.24.mlp.gate_proj: 5
|
| 182 |
+
model.layers.14.mlp.up_proj: 6
|
| 183 |
+
model.layers.17.self_attn.v_proj: 8
|
| 184 |
+
model.layers.7.self_attn.q_proj: 7
|
| 185 |
+
model.layers.28.self_attn.k_proj: 8
|
| 186 |
+
model.layers.21.self_attn.q_proj: 8
|
| 187 |
+
model.layers.29.self_attn.o_proj: 6
|
| 188 |
+
model.layers.7.mlp.down_proj: 5
|
| 189 |
+
model.layers.16.self_attn.k_proj: 8
|
| 190 |
+
model.layers.17.self_attn.o_proj: 6
|
| 191 |
+
model.layers.34.mlp.up_proj: 6
|
| 192 |
+
model.layers.21.mlp.gate_proj: 5
|
| 193 |
+
model.layers.16.self_attn.v_proj: 8
|
| 194 |
+
model.layers.24.mlp.up_proj: 5
|
| 195 |
+
model.layers.34.self_attn.q_proj: 8
|
| 196 |
+
model.layers.8.mlp.up_proj: 5
|
| 197 |
+
model.layers.11.mlp.down_proj: 5
|
| 198 |
+
model.layers.7.mlp.up_proj: 5
|
| 199 |
+
model.layers.35.mlp.gate_proj: 7
|
| 200 |
+
model.layers.28.self_attn.v_proj: 8
|
| 201 |
+
model.layers.4.mlp.gate_proj: 5
|
| 202 |
+
model.layers.16.mlp.up_proj: 5
|
| 203 |
+
model.layers.15.self_attn.v_proj: 8
|
| 204 |
+
model.layers.19.mlp.up_proj: 5
|
| 205 |
+
model.layers.8.mlp.down_proj: 5
|
| 206 |
+
model.layers.12.mlp.gate_proj: 6
|
| 207 |
+
model.layers.15.self_attn.k_proj: 8
|
| 208 |
+
model.layers.14.self_attn.o_proj: 6
|
| 209 |
+
model.layers.22.self_attn.q_proj: 8
|
| 210 |
+
model.layers.22.mlp.down_proj: 5
|
| 211 |
+
model.layers.4.self_attn.q_proj: 6
|
| 212 |
+
model.layers.14.self_attn.v_proj: 8
|
| 213 |
+
model.layers.26.mlp.up_proj: 5
|
| 214 |
+
model.layers.29.mlp.up_proj: 5
|
| 215 |
+
model.layers.5.mlp.up_proj: 5
|
| 216 |
+
model.layers.1.mlp.gate_proj: 4
|
| 217 |
+
model.layers.27.mlp.down_proj: 5
|
| 218 |
+
model.layers.23.self_attn.q_proj: 7
|
| 219 |
+
model.layers.5.self_attn.q_proj: 6
|
| 220 |
+
model.layers.33.mlp.down_proj: 5
|
| 221 |
+
model.layers.17.mlp.gate_proj: 5
|
| 222 |
+
model.layers.15.self_attn.o_proj: 6
|
| 223 |
+
model.layers.14.self_attn.k_proj: 8
|
| 224 |
+
model.layers.12.self_attn.k_proj: 8
|
| 225 |
+
model.layers.13.self_attn.o_proj: 6
|
| 226 |
+
model.layers.29.mlp.gate_proj: 5
|
| 227 |
+
model.layers.25.self_attn.q_proj: 7
|
| 228 |
+
model.layers.30.mlp.up_proj: 5
|
| 229 |
+
model.layers.3.mlp.gate_proj: 4
|
| 230 |
+
model.layers.19.mlp.down_proj: 5
|
| 231 |
+
model.layers.3.self_attn.q_proj: 6
|
| 232 |
+
model.layers.20.mlp.up_proj: 5
|
| 233 |
+
model.layers.30.self_attn.q_proj: 7
|
| 234 |
+
model.layers.25.mlp.down_proj: 5
|
| 235 |
+
model.layers.12.self_attn.v_proj: 8
|
| 236 |
+
model.layers.3.mlp.up_proj: 4
|
| 237 |
+
model.layers.31.mlp.down_proj: 5
|
| 238 |
+
model.layers.15.mlp.gate_proj: 5
|
| 239 |
+
model.layers.24.self_attn.q_proj: 8
|
| 240 |
+
model.layers.2.self_attn.q_proj: 6
|
| 241 |
+
model.layers.6.mlp.gate_proj: 6
|
| 242 |
+
model.layers.12.self_attn.o_proj: 6
|
| 243 |
+
model.layers.13.self_attn.k_proj: 8
|
| 244 |
+
model.layers.13.self_attn.v_proj: 8
|
| 245 |
+
model.layers.34.mlp.down_proj: 5
|
| 246 |
+
model.layers.10.mlp.gate_proj: 6
|
| 247 |
+
model.layers.10.mlp.up_proj: 6
|
| 248 |
+
model.layers.20.mlp.down_proj: 5
|
| 249 |
+
model.layers.31.self_attn.q_proj: 7
|
| 250 |
+
model.layers.22.mlp.up_proj: 5
|
| 251 |
+
model.layers.32.self_attn.q_proj: 8
|
| 252 |
+
model.layers.8.self_attn.v_proj: 8
|
| 253 |
+
model.layers.5.mlp.down_proj: 5
|
| 254 |
+
model.layers.10.self_attn.v_proj: 8
|
| 255 |
+
model.layers.1.mlp.up_proj: 4
|
| 256 |
+
model.layers.11.self_attn.o_proj: 6
|
| 257 |
+
model.layers.10.self_attn.k_proj: 8
|
| 258 |
+
model.layers.19.self_attn.q_proj: 8
|
| 259 |
+
model.layers.23.mlp.gate_proj: 5
|
| 260 |
+
model.layers.8.self_attn.k_proj: 8
|
| 261 |
+
model.layers.32.mlp.up_proj: 6
|
| 262 |
+
model.layers.1.self_attn.q_proj: 6
|
| 263 |
+
model.layers.9.self_attn.o_proj: 6
|
| 264 |
+
model.layers.9.mlp.gate_proj: 6
|
| 265 |
+
model.layers.13.mlp.down_proj: 5
|
| 266 |
+
model.layers.27.self_attn.q_proj: 8
|
| 267 |
+
model.layers.0.mlp.down_proj: 5
|
| 268 |
+
model.layers.11.self_attn.v_proj: 8
|
| 269 |
+
model.layers.33.self_attn.q_proj: 7
|
| 270 |
+
model.layers.9.self_attn.v_proj: 8
|
| 271 |
+
model.layers.12.mlp.up_proj: 6
|
| 272 |
+
model.layers.8.self_attn.o_proj: 6
|
| 273 |
+
model.layers.0.self_attn.q_proj: 6
|
| 274 |
+
model.layers.9.self_attn.k_proj: 8
|
| 275 |
+
model.layers.26.self_attn.q_proj: 8
|
| 276 |
+
model.layers.16.mlp.down_proj: 5
|
| 277 |
+
model.layers.32.mlp.gate_proj: 6
|
| 278 |
+
model.layers.18.self_attn.q_proj: 7
|
| 279 |
+
model.layers.11.self_attn.k_proj: 8
|
| 280 |
+
model.layers.10.self_attn.o_proj: 6
|
| 281 |
+
model.layers.26.mlp.gate_proj: 5
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_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/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
humming/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_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/Qwen3-8B/ll_bsearch_kl0.005_eap0.99_sha_bw5.70_4-5-6-7-8bit_seed42/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|