Imablank commited on
Commit
108fd59
1 Parent(s): 14644bd
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ thumbnail: null
5
+ tags:
6
+ - text generation
7
+ - conversational
8
+ pipeline_tag: text-generation
9
+ inference: false
10
+ ---
11
+ <h1 style="text-align: center">Pygmalion 7B</h1>
12
+ <h2 style="text-align: center">A conversational LLaMA fine-tune.</h2>
13
+
14
+ ## Model Details
15
+
16
+ Converted from the XORs weights from PygmalionAI's release https://huggingface.co/PygmalionAI/pygmalion-7b
17
+
18
+ Pygmalion 7B is a dialogue model based on Meta's LLaMA-7B.
19
+
20
+ This is version 1. It has been fine-tuned using a subset of the data from Pygmalion-6B-v8-pt4, for those of you familiar with the project.
21
+
22
+ ## Prompting
23
+
24
+ The model was trained on the usual Pygmalion persona + chat format, so any of the usual UIs should already handle everything correctly. If you're using the model directly, this is the expected formatting:
25
+
26
+ ```
27
+ [CHARACTER]'s Persona: [A few sentences about the character you want the model to play]
28
+ <START>
29
+ [DIALOGUE HISTORY]
30
+ You: [User's input message here]
31
+ [CHARACTER]:
32
+ ```
33
+
34
+ Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is a sliding window of chat history so the model can have conversational context to draw from. Here's a concrete example:
35
+
36
+ ```
37
+ Assistant's Persona: Assistant is a highly intelligent language model trained to comply with user requests.
38
+ <START>
39
+ Assistant: Hello! How may I help you today?
40
+ You: What is Zork?
41
+ Assistant:
42
+ ```
43
+
44
+ Which will generate something like:
45
+
46
+ ```
47
+ Zork is an interactive fiction computer game created in the 1970s by Infocom, Inc., which was later acquired by Activision Blizzard. It is widely considered one of the most influential games ever made and has been credited with popularizing text-based adventure games. The original version of Zork was written in the programming language MACRO-10, but it was ported to many other platforms over the years."
48
+ ```
49
+
50
+ The model will automatically emit an end-of-text token (`</s>`) when it judges that the response is complete.
51
+
52
+ ## Limitations and biases
53
+
54
+ The intended use-case for this model is fictional conversation for entertainment purposes. Any other sort of usage is out of scope.
55
+
56
+ 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.
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pygmalion-7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "badwordsids": [
7
+ [
8
+ 0
9
+ ]
10
+ ],
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "max_position_embeddings": 2048,
18
+ "max_sequence_length": 2048,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "pad_token_id": 0,
23
+ "rms_norm_eps": 1e-06,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.28.1",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:958bd8a8e45ab7b0ccd50620638b02814fab5598ad223485a31c4e052d237529
3
+ size 9976579148
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d495f000fbc0473663f288004b9cd8fa02119a9ca9f3f1a5ae4a7d2187dd2f7
3
+ size 3500297420
model.safetensors.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476839424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
117
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
127
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
137
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
147
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
157
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
167
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
177
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
187
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
197
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
207
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
217
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
227
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
237
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
247
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
257
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
267
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
277
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
287
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
297
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
302
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
307
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
308
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
317
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
318
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
327
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.norm.weight": "model-00002-of-00002.safetensors"
329
+ }
330
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476839424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
329
+ }
330
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
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": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "padding_side": "right",
24
+ "sp_model_kwargs": {},
25
+ "special_tokens_map_file": "special_tokens_map.json",
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }