zhoudong commited on
Commit
2f3d2a9
1 Parent(s): c571390

init_model

Browse files
config.json CHANGED
@@ -11,21 +11,21 @@
11
  "hidden_size": 2560,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 7168,
14
- "max_position_embeddings": 4096,
15
- "max_sequence_length": 4096,
16
  "mlp_bias": false,
17
  "model_type": "llama",
18
  "num_attention_heads": 40,
19
  "num_hidden_layers": 32,
20
  "num_key_value_heads": 10,
21
- "pad_token_id": 0,
22
  "pretraining_tp": 1,
23
  "rms_norm_eps": 1e-05,
24
  "rope_scaling": null,
25
  "rope_theta": 5000000.0,
26
  "tie_word_embeddings": false,
27
  "torch_dtype": "bfloat16",
28
- "transformers_version": "4.44.2",
29
- "use_cache": false,
30
  "vocab_size": 122880
31
  }
 
11
  "hidden_size": 2560,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 7168,
14
+ "max_position_embeddings": 32768,
15
+ "max_sequence_length": 32768,
16
  "mlp_bias": false,
17
  "model_type": "llama",
18
  "num_attention_heads": 40,
19
  "num_hidden_layers": 32,
20
  "num_key_value_heads": 10,
21
+ "pad_token_id": 120002,
22
  "pretraining_tp": 1,
23
  "rms_norm_eps": 1e-05,
24
  "rope_scaling": null,
25
  "rope_theta": 5000000.0,
26
  "tie_word_embeddings": false,
27
  "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.43.4",
29
+ "use_cache": true,
30
  "vocab_size": 122880
31
  }
generation_config.json CHANGED
@@ -1,6 +1,9 @@
1
  {
2
  "_from_model_config": true,
3
- "eos_token_id": 120005,
4
- "pad_token_id": 0,
5
- "transformers_version": "4.44.2"
 
 
 
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 120005,
5
+ 120000
6
+ ],
7
+ "pad_token_id": 120002,
8
+ "transformers_version": "4.43.4"
9
  }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873db75b9180027346193bbb308df05db99adae82f2868b26a262903e8311328
3
+ size 4985007328
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6621f57a226758d49f7a6225664d492af75857100a8daa21705ec6c92b4a1351
3
+ size 845441696
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5830415360
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.norm.weight": "model-00002-of-00002.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|turn_end>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|pad|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "120000": {
4
+ "content": "<|eos|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "120001": {
12
+ "content": "<|unk|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "120002": {
20
+ "content": "<|pad|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "120003": {
28
+ "content": "<|role_start|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "120004": {
36
+ "content": "<|role_end|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "120005": {
44
+ "content": "<|turn_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "120006": {
52
+ "content": "<|code_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "120007": {
60
+ "content": "<|code_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "120008": {
68
+ "content": "<|commit_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "120009": {
76
+ "content": "<|commit_end|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "120010": {
84
+ "content": "<|diff_start|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "120011": {
92
+ "content": "<|diff_end|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "120012": {
100
+ "content": "<|code_execution_start|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "120013": {
108
+ "content": "<|code_execution_end|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "120014": {
116
+ "content": "<|image_start|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "120015": {
124
+ "content": "<|image_end|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "120016": {
132
+ "content": "<|image_pad|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "120017": {
140
+ "content": "<|video_start|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "120018": {
148
+ "content": "<|video_end|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "120019": {
156
+ "content": "<|video_pad|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "120020": {
164
+ "content": "<|audio_start|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "120021": {
172
+ "content": "<|audio_end|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "120022": {
180
+ "content": "<|audio_pad|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "120023": {
188
+ "content": "<|function_start|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "120024": {
196
+ "content": "<|function_end|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "120025": {
204
+ "content": "<|turn_end>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ }
211
+ },
212
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|role_start|>system<|role_end|>你是Megrez-3B-Instruct,将针对用户的问题给出详细的、积极的回答。<|turn_end|>' }}{% endif %}{{ '<|role_start|>' + message['role'] + '<|role_end|>' + message['content'] + '<|turn_end|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|role_start|>assistant<|role_end|>' }}{% endif %}",
213
+ "clean_up_tokenization_spaces": true,
214
+ "eos_token": "<|turn_end>",
215
+ "model_max_length": 32768,
216
+ "pad_token": "<|pad|>",
217
+ "padding_side": "right",
218
+ "tokenizer_class": "PreTrainedTokenizerFast"
219
+ }