taozi555 commited on
Commit
c4a6fcb
1 Parent(s): 5eb62c6
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ thumbnail: null
5
+ tags:
6
+ - text generation
7
+ - instruct
8
+ pipeline_tag: text-generation
9
+ inference: false
10
+ license: llama2
11
+ datasets:
12
+ - PygmalionAI/PIPPA
13
+ - Open-Orca/OpenOrca
14
+ - Norquinal/claude_multiround_chat_30k
15
+ - jondurbin/airoboros-gpt4-1.4.1
16
+ - databricks/databricks-dolly-15k
17
+ ---
18
+ <h1 style="text-align: center">Mythalion 13B</h1>
19
+ <h2 style="text-align: center">A merge of Pygmalion-2 13B and MythoMax 13B</h2>
20
+
21
+ ## Model Details
22
+
23
+ The long-awaited release of our new models based on Llama-2 is finally here. This model was created in
24
+ collaboration with [Gryphe](https://huggingface.co/Gryphe), a mixture of our [Pygmalion-2 13B](https://huggingface.co/PygmalionAI/pygmalion-2-13b)
25
+ and Gryphe's [Mythomax L2 13B](https://huggingface.co/Gryphe/MythoMax-L2-13b).
26
+
27
+ Finer details of the merge are available in [our blogpost](https://pygmalionai.github.io/blog/posts/introducing_pygmalion_2/#mythalion-13b).
28
+ According to our testers, this model seems to outperform MythoMax in RP/Chat. **Please make sure you follow the recommended
29
+ generation settings for SillyTavern [here](https://pygmalionai.github.io/blog/posts/introducing_pygmalion_2/#sillytavern) for
30
+ the best results!**
31
+
32
+ This model is freely available for both commercial and non-commercial use, as per the Llama-2 license.
33
+
34
+
35
+ ## Prompting
36
+
37
+ This model can be prompted using both the Alpaca and [Pygmalion formatting](https://huggingface.co/PygmalionAI/pygmalion-2-13b#prompting).
38
+
39
+ **Alpaca formatting**:
40
+ ```
41
+ ### Instruction:
42
+ <prompt>
43
+
44
+ ### Response:
45
+ <leave a newline blank for model to respond>
46
+ ```
47
+
48
+ **Pygmalion/Metharme formatting**:
49
+ ```
50
+ <|system|>Enter RP mode. Pretend to be {{char}} whose persona follows:
51
+ {{persona}}
52
+
53
+ You shall reply to the user while staying in character, and generate long responses.
54
+ <|user|>Hello!<|model|>{model's response goes here}
55
+
56
+ ```
57
+
58
+
59
+ The model has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
60
+
61
+ The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input.
62
+ The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to
63
+ form a conversation history.
64
+
65
+ ## Limitations and biases
66
+
67
+ The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope.
68
+
69
+ As such, it was **not** fine-tuned to be safe and harmless: the base model _and_ this fine-tune have been trained on data known to contain profanity and texts that are lewd or otherwise offensive. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading.
70
+
71
+ ## Acknowledgements
72
+ We would like to thank [SpicyChat](https://spicychat.ai/) for sponsoring the training for the [Pygmalion-2 13B](https://huggingface.co/PygmalionAI/pygmalion-2-13b) model.
73
+
74
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PygmalionAI/mythalion-13b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "badwordsids": "[[29961], [14352], [24630], [29962], [11759], [15974], [5519], [25473], [18899], [25901], [7110], [9341], [13531], [518], [9310], [2636], [3366], [21069], [11970], [23098], [16733], [21298], [18173], [10846], [3816], [28513], [15625], [23192], [28166], [10062], [1385], [11724], [3108], [15555], [10834], [10370], [14330], [1822], [12436], [5262], [17094], [10725], [17077], [11424], [4197], [24406], [13359], [17531], [24566], [23076], [4514], [13192], [19942], [16261], [7072], [6024], [1402], [1839], [2033], [13970], [850], [5913], [28895], [5387], [8308], [24927], [5691], [12940], [19997], [18959], [11287], [16862], [4638], [22322], [29861], [21251], [14704], [17548], [12452], [17288], [23160], [24960], [8219], [18024], [5539], [7464], [27865], [29588], [20068], [19660], [27706], [22896], [24264], [12258], [2314], [4400], [5586], [12622], [6796], [7226], [21939], [18456], [14178], [21540], [21945], [14664], [16215], [10338], [17361], [7503], [13769], [26073], [9601], [26909], [7961], [8999], [20840], [16272], [21545], [3199], [10514], [5159], [22689], [6525], [20526], [27077], [18017]]",
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.33.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.33.0.dev0",
7
+ "use_cache": false
8
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26031728640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
368
+ "model.norm.weight": "model-00003-of-00003.safetensors"
369
+ }
370
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c65db0989fe7cc256f6b560f78382e5381d15aac89cbf758cea33e540322656
3
+ size 7207668064
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808abdca2614ac2d07fbbb62651c6c72521ef6f0d635dfe51564a9aaba1459d8
3
+ size 9948719433
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f23320df7f7573c7c8064bbe892e35e0a1bc17aa53f5bcb888a3df0254d3f8
3
+ size 9904155408
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d456b3a446ada56e074866e0859387c3510ff139699b67936c4fc4913223dd
3
+ size 6178978207
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26031728640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
323
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
324
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
327
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
328
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
329
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
330
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
331
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
332
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
333
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
334
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
335
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
336
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
337
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
338
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
339
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
340
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
341
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
342
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
343
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
344
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
345
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
346
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
347
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
348
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
349
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
350
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
351
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
352
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
353
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
354
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
355
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
356
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
357
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
358
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
359
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
360
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
361
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
362
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
363
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
365
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
366
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
367
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
369
+ }
370
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "spaces_between_special_tokens": false,
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "trust_remote_code": false,
29
+ "unk_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "use_default_system_prompt": true,
38
+ "use_fast": true
39
+ }