Hugging Face's logo

ubowang
/
critique-32b-instruct

Safetensors
qwen2
Model card Files Community
ubowang commited on
Commit
1f64483
·
verified ·
1 Parent(s): 1e06ca9

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. config.json +11 -10
  2. generation_config.json +2 -10
  3. model-00001-of-00004.safetensors +3 -0
  4. model-00002-of-00004.safetensors +3 -0
  5. model-00003-of-00004.safetensors +3 -0
  6. model-00004-of-00004.safetensors +3 -0
  7. model.safetensors.index.json +340 -772
  8. special_tokens_map.json +1 -1
  9. tokenizer_config.json +2 -2
  10. trainer_state.json +11 -67
  11. training_args.bin +2 -2
config.json CHANGED
@@ -1,29 +1,30 @@
1
  {
2
- "_name_or_path": "/gpfs/public/research/xy/yubowang/models/Qwen2.5-32B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
  "hidden_act": "silu",
10
- "hidden_size": 5120,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 27648,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 70,
15
  "model_type": "qwen2",
16
- "num_attention_heads": 40,
17
- "num_hidden_layers": 64,
18
- "num_key_value_heads": 8,
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
- "rope_theta": 1000000.0,
22
  "sliding_window": null,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.1",
26
  "use_cache": false,
 
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
29
  }
 
1
  {
2
+ "_name_or_path": "/gpfs/public/research/xy/yubowang/models/Qwen2.5-Math-7B",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
  "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 4096,
14
+ "max_window_layers": 28,
15
  "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
+ "rope_theta": 10000,
22
  "sliding_window": null,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.1",
26
  "use_cache": false,
27
+ "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 152064
30
  }
generation_config.json CHANGED
@@ -1,14 +1,6 @@
1
  {
2
  "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.05,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
  "transformers_version": "4.46.1"
14
  }
 
1
  {
2
  "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
 
 
 
 
 
 
 
 
5
  "transformers_version": "4.46.1"
6
  }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a824b23c1953868ce57893deee18b2e26c0db399c188fca295dabe0b63605fbf
3
+ size 4877660776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b8d1ceea9bb99d5c22bbc93318cffb355b3e322f0b1867e9a856ac6e03081d
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa676c6842c92063bc0e91a97d14f407cc13cf6da2d4ee41a93638b3fe73a22f
3
+ size 4330865200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92864406b9c9fdf8f783576369c3bb955d3a479803a54d3c98329bcff03b36e
3
+ size 1089994880
model.safetensors.index.json CHANGED
@@ -1,778 +1,346 @@
1
  {
2
  "metadata": {
3
- "total_size": 65527752704
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00014-of-00014.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
13
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
16
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
17
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
18
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
19
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
- "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
26
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
29
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
31
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
32
- "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
33
- "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
34
- "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
35
- "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
36
- "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
37
- "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
38
- "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
39
- "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
40
- "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
41
- "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
42
- "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
43
- "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
44
- "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
45
- "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
46
- "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
47
- "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
48
- "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
49
- "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
50
- "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
51
- "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
52
- "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
53
- "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
54
- "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
55
- "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
56
- "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
57
- "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
58
- "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
59
- "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
60
- "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
61
- "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
62
- "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
63
- "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
64
- "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
65
- "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
66
- "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
67
- "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
68
- "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
69
- "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
70
- "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
71
- "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
72
- "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
73
- "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
74
- "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
75
- "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
76
- "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
77
- "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
78
- "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
79
- "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
80
- "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
81
- "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
82
- "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
83
- "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
84
- "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
85
- "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
86
- "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
87
- "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
88
- "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
89
- "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
90
- "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
91
- "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
92
- "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
93
- "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
94
- "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
95
- "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
96
- "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
97
- "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
98
- "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
99
- "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
100
- "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
101
- "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
102
- "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
103
- "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
104
- "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
105
- "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
106
- "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
107
- "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
108
- "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
109
- "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
110
- "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
111
- "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
112
- "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
113
- "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
114
- "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
115
- "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
116
- "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
117
- "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
118
- "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
119
- "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
120
- "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
121
- "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
122
- "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
123
- "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
124
- "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
125
- "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
126
- "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
127
- "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
128
- "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
129
- "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
130
- "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
131
- "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
132
- "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
133
- "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
134
- "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
135
- "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
136
- "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
137
- "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
138
- "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
139
- "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
140
- "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
141
- "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
142
- "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
143
- "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
144
- "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
145
- "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
146
- "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
147
- "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
148
- "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
149
- "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
150
- "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
151
- "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
152
- "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
153
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
154
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
155
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
156
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
157
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
158
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
159
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
160
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
161
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
162
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
163
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
164
- "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
165
- "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
166
- "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
167
- "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
168
- "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
169
- "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
170
- "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
171
- "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
172
- "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
173
- "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
174
- "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
175
- "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
176
- "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
177
- "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
178
- "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
179
- "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
180
- "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
181
- "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
182
- "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
183
- "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
184
- "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
185
- "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
186
- "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
187
- "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
188
- "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
189
- "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
190
- "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
191
- "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
192
- "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
193
- "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
194
- "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
195
- "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
196
- "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
197
- "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
198
- "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
199
- "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
200
- "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
201
- "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
202
- "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
203
- "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
204
- "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
205
- "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
206
- "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
207
- "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
208
- "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
209
- "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
210
- "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
211
- "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
212
- "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
213
- "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
214
- "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
215
- "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
216
- "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
217
- "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
218
- "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
219
- "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
220
- "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
221
- "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
222
- "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
223
- "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
224
- "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
225
- "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
226
- "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
227
- "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
228
- "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
229
- "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
230
- "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
231
- "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
232
- "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
233
- "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
234
- "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
235
- "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
236
- "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
237
- "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
238
- "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
239
- "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
240
- "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
241
- "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
242
- "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
243
- "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
244
- "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
245
- "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
246
- "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
247
- "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
248
- "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
249
- "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
250
- "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
251
- "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
252
- "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
253
- "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
254
- "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
255
- "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
256
- "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
257
- "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
258
- "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
259
- "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
260
- "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
261
- "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
262
- "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
263
- "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
264
- "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
265
- "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
266
- "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
267
- "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
268
- "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
269
- "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
270
- "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
271
- "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
272
- "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
273
- "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
274
- "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
275
- "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
276
- "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
277
- "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
278
- "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
279
- "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
280
- "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
281
- "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
282
- "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
283
- "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
- "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
285
- "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
286
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
287
- "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
288
- "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
289
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
290
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
291
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
292
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
293
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
294
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
295
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
296
- "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
297
- "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
298
- "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
299
- "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
300
- "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
301
- "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
302
- "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
303
- "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
304
- "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
305
- "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
306
- "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
307
- "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
308
- "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
309
- "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
310
- "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
311
- "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
312
- "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
313
- "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
314
- "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
315
- "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
316
- "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
317
- "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
318
- "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
319
- "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
320
- "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
321
- "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
322
- "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
323
- "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
324
- "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
325
- "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
326
- "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
327
- "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
328
- "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
329
- "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
330
- "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
331
- "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
332
- "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
333
- "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
334
- "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
335
- "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
336
- "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
337
- "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
338
- "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
339
- "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
340
- "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
341
- "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
342
- "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
343
- "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
344
- "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
345
- "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
346
- "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
347
- "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
348
- "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
349
- "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
350
- "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
351
- "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
352
- "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
353
- "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
354
- "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
355
- "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
356
- "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
357
- "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
358
- "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
359
- "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
360
- "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
361
- "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
362
- "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
363
- "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
364
- "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
365
- "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
366
- "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
367
- "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
368
- "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
369
- "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
370
- "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
371
- "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
372
- "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
373
- "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
374
- "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
375
- "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
376
- "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
377
- "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
378
- "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
379
- "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
380
- "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
381
- "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
382
- "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
383
- "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
384
- "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
385
- "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
386
- "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
387
- "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
388
- "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
389
- "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
390
- "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
391
- "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
392
- "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
393
- "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
394
- "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
395
- "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
396
- "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
397
- "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
398
- "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
399
- "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
400
- "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
401
- "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
402
- "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
403
- "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
404
- "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
405
- "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
406
- "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
407
- "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
408
- "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
409
- "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
410
- "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
411
- "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
412
- "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
413
- "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
414
- "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
415
- "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
- "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
417
- "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
418
- "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
419
- "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
420
- "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
421
- "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
422
- "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
423
- "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
424
- "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
425
- "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
426
- "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
427
- "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
428
- "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
429
- "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
430
- "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
431
- "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
432
- "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
433
- "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
434
- "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
435
- "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
436
- "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
437
- "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
438
- "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
439
- "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
440
- "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
441
- "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
442
- "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
443
- "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
444
- "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
445
- "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
446
- "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
447
- "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
448
- "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
449
- "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
450
- "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
451
- "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
452
- "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
453
- "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
454
- "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
455
- "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
456
- "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
457
- "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
458
- "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
459
- "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
460
- "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
461
- "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
462
- "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
463
- "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
464
- "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
465
- "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
466
- "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
467
- "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
468
- "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
469
- "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
470
- "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
471
- "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
472
- "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
473
- "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
474
- "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
475
- "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
476
- "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
477
- "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
478
- "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
479
- "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
480
- "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
481
- "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
482
- "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
483
- "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
484
- "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
485
- "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
486
- "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
487
- "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
488
- "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
489
- "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
490
- "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
491
- "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
492
- "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
493
- "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
494
- "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
495
- "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
496
- "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
497
- "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
498
- "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
499
- "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
500
- "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
501
- "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
502
- "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
503
- "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
504
- "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
505
- "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
506
- "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
507
- "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
508
- "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
509
- "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
510
- "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
511
- "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
512
- "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
513
- "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
514
- "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
515
- "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
516
- "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
517
- "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
518
- "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
519
- "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
520
- "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
521
- "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
522
- "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
523
- "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
524
- "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
525
- "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
526
- "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
527
- "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
528
- "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
529
- "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
530
- "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
531
- "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
532
- "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
533
- "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
534
- "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
535
- "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
536
- "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
537
- "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
538
- "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
539
- "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
540
- "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
541
- "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
542
- "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
543
- "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
544
- "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
545
- "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
546
- "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
547
- "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
- "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
549
- "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
550
- "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
551
- "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
552
- "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
553
- "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
554
- "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
555
- "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
556
- "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
557
- "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
558
- "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
559
- "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
560
- "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
561
- "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
562
- "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
563
- "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
564
- "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
565
- "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
566
- "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
567
- "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
568
- "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
569
- "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
570
- "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
571
- "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
572
- "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
573
- "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
574
- "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
575
- "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
576
- "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
577
- "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
578
- "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
579
- "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
580
- "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
581
- "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
582
- "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
583
- "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
584
- "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
585
- "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
586
- "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
587
- "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
588
- "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
589
- "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
590
- "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
591
- "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
592
- "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
593
- "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
594
- "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
595
- "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
596
- "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
597
- "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
598
- "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
599
- "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
600
- "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
601
- "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
602
- "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
603
- "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
604
- "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
605
- "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
606
- "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
607
- "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
608
- "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
609
- "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
610
- "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
611
- "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
612
- "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
613
- "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
614
- "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
615
- "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
616
- "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
617
- "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
618
- "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
619
- "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
620
- "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
621
- "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
622
- "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
623
- "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
624
- "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
625
- "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
626
- "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
627
- "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
628
- "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
629
- "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
630
- "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
631
- "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
632
- "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
633
- "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
634
- "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
635
- "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
636
- "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
637
- "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
638
- "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
639
- "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
640
- "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
641
- "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
642
- "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
643
- "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
644
- "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
645
- "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
646
- "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
647
- "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
648
- "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
649
- "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
650
- "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
651
- "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
652
- "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
653
- "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
654
- "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
655
- "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
656
- "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
657
- "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
658
- "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
659
- "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
660
- "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
661
- "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
662
- "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
663
- "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
664
- "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
665
- "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
666
- "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
667
- "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
668
- "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
669
- "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
670
- "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
671
- "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
672
- "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
673
- "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
674
- "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
675
- "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
676
- "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
677
- "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
678
- "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
679
- "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
- "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
- "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
- "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
- "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
686
- "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
- "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
- "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
689
- "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
- "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
691
- "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
692
- "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
693
- "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
694
- "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
695
- "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
696
- "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
697
- "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
698
- "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
699
- "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
700
- "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
701
- "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
702
- "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
703
- "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
704
- "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
705
- "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
706
- "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
707
- "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
708
- "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
709
- "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
710
- "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
711
- "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
712
- "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
713
- "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
714
- "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
715
- "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
716
- "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
717
- "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
718
- "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
719
- "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
720
- "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
721
- "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
722
- "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
723
- "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
724
- "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
725
- "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
726
- "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
727
- "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
728
- "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
729
- "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
730
- "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
731
- "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
732
- "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
733
- "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
734
- "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
735
- "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
736
- "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
737
- "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
738
- "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
739
- "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
740
- "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
741
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
742
- "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
743
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
744
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
745
- "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
746
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
747
- "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
748
- "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
749
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
750
- "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
751
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
752
- "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
753
- "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
754
- "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
755
- "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
756
- "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
757
- "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
758
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
759
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
760
- "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
761
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
762
- "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
763
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
764
- "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
765
- "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
766
- "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
767
- "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
768
- "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
769
- "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
770
- "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
771
- "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
772
- "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
773
- "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
774
- "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
775
- "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
776
- "model.norm.weight": "model-00014-of-00014.safetensors"
777
  }
778
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 15231233024
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
345
  }
346
  }
special_tokens_map.json CHANGED
@@ -15,7 +15,7 @@
15
  "<|video_pad|>"
16
  ],
17
  "eos_token": {
18
- "content": "<|im_end|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
 
15
  "<|video_pad|>"
16
  ],
17
  "eos_token": {
18
+ "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -195,9 +195,9 @@
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
- "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
- "eos_token": "<|im_end|>",
201
  "errors": "replace",
202
  "model_max_length": 131072,
203
  "pad_token": "<|endoftext|>",
 
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
  "errors": "replace",
202
  "model_max_length": 131072,
203
  "pad_token": "<|endoftext|>",
trainer_state.json CHANGED
@@ -1,89 +1,33 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.064,
5
  "eval_steps": 500,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0064,
13
- "grad_norm": 4.475914221067157,
14
- "learning_rate": 1.0000000000000002e-06,
15
- "loss": 0.5291,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0128,
20
- "grad_norm": 4.702447829309332,
21
- "learning_rate": 2.0000000000000003e-06,
22
- "loss": 0.5404,
23
  "step": 2
24
- },
25
- {
26
- "epoch": 0.0192,
27
- "grad_norm": 4.4349012153365965,
28
- "learning_rate": 3e-06,
29
- "loss": 0.5352,
30
- "step": 3
31
- },
32
- {
33
- "epoch": 0.0256,
34
- "grad_norm": 3.999832713661061,
35
- "learning_rate": 4.000000000000001e-06,
36
- "loss": 0.5406,
37
- "step": 4
38
- },
39
- {
40
- "epoch": 0.032,
41
- "grad_norm": 2.6646732022628057,
42
- "learning_rate": 5e-06,
43
- "loss": 0.4806,
44
- "step": 5
45
- },
46
- {
47
- "epoch": 0.0384,
48
- "grad_norm": 2.2477891093155242,
49
- "learning_rate": 4.999458946515808e-06,
50
- "loss": 0.4428,
51
- "step": 6
52
- },
53
- {
54
- "epoch": 0.0448,
55
- "grad_norm": 1.9598978484642742,
56
- "learning_rate": 4.997836020254328e-06,
57
- "loss": 0.4133,
58
- "step": 7
59
- },
60
- {
61
- "epoch": 0.0512,
62
- "grad_norm": 1.2928897559495274,
63
- "learning_rate": 4.995131923687488e-06,
64
- "loss": 0.3468,
65
- "step": 8
66
- },
67
- {
68
- "epoch": 0.0576,
69
- "grad_norm": 1.1965464748112815,
70
- "learning_rate": 4.991347827263983e-06,
71
- "loss": 0.3576,
72
- "step": 9
73
- },
74
- {
75
- "epoch": 0.064,
76
- "grad_norm": 1.0746415845607094,
77
- "learning_rate": 4.986485368902656e-06,
78
- "loss": 0.3336,
79
- "step": 10
80
  }
81
  ],
82
  "logging_steps": 1,
83
  "max_steps": 156,
84
  "num_input_tokens_seen": 0,
85
  "num_train_epochs": 1,
86
- "save_steps": 10,
87
  "stateful_callbacks": {
88
  "TrainerControl": {
89
  "args": {
@@ -96,8 +40,8 @@
96
  "attributes": {}
97
  }
98
  },
99
- "total_flos": 31686818791424.0,
100
- "train_batch_size": 1,
101
  "trial_name": null,
102
  "trial_params": null
103
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0128,
5
  "eval_steps": 500,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0064,
13
+ "grad_norm": 10.505431462007456,
14
+ "learning_rate": 3.125e-07,
15
+ "loss": 0.5487,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0128,
20
+ "grad_norm": 11.188743300643402,
21
+ "learning_rate": 6.25e-07,
22
+ "loss": 0.5546,
23
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  }
25
  ],
26
  "logging_steps": 1,
27
  "max_steps": 156,
28
  "num_input_tokens_seen": 0,
29
  "num_train_epochs": 1,
30
+ "save_steps": 2,
31
  "stateful_callbacks": {
32
  "TrainerControl": {
33
  "args": {
 
40
  "attributes": {}
41
  }
42
  },
43
+ "total_flos": 3239472660480.0,
44
+ "train_batch_size": 8,
45
  "trial_name": null,
46
  "trial_params": null
47
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c3a07ebf2bcd08193e8e2ad3899159ef56849cbde240a35fcb45a07c2c462ba
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f4fcf9602649b7f324934a2cd858fa52a137728be066ee91e07e33671a8483
3
+ size 7352