CharlesGao commited on
Commit
e9ce565
1 Parent(s): 9ec436d

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b",
3
+ "architectures": [
4
+ "InternLM2ForCausalLM"
5
+ ],
6
+ "attn_implementation": "eager",
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
9
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
10
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
11
+ },
12
+ "bias": false,
13
+ "bos_token_id": 1,
14
+ "eos_token_id": 2,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 32768,
20
+ "model_type": "internlm2",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 2,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 1000000,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.3",
31
+ "use_cache": true,
32
+ "vocab_size": 100738
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.39.3"
7
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc97d0d2a251e2fe050142fe6aadf8aeb8752985038d6db05be780a3bfbef73
3
+ size 4905372536
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b93c26e2d9012e885938836b11f3b88ec4b7c7a46f52f3a641604088eac12cc
3
+ size 4999811584
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5bfc1da4669471e03347056743ea641f4d820470026d46d3452a8aab27771d
3
+ size 4999811632
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0554941d497d6f44c08418f9b51106699a149330f55e0f4c9e77c897161c2d1f
3
+ size 4832006256
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82a94ab8f4ec5dd3e7f0cd49b8ef6cc5e99238c91693ead08ad2856857317d5
3
+ size 4999811624
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a237a934727a7b53647ae6fe09811408c0f823168046f0bc9c26e2b5efc4216f
3
+ size 4832055712
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d352051fed0404c3c552852b8451a60225a7fc62e22d4db79adb1b9fb89b7138
3
+ size 3166732512
model.safetensors.index.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32735576064
4
+ },
5
+ "weight_map": {
6
+ "model.layers.0.attention.wo.weight": "model-00001-of-00007.safetensors",
7
+ "model.layers.0.attention.wqkv.weight": "model-00001-of-00007.safetensors",
8
+ "model.layers.0.attention_norm.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.feed_forward.w1.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.feed_forward.w2.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.feed_forward.w3.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.1.attention.wo.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.1.attention.wqkv.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.1.attention_norm.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.1.feed_forward.w1.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.1.feed_forward.w2.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.1.feed_forward.w3.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.1.ffn_norm.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.10.attention.wo.weight": "model-00003-of-00007.safetensors",
21
+ "model.layers.10.attention.wqkv.weight": "model-00003-of-00007.safetensors",
22
+ "model.layers.10.attention_norm.weight": "model-00003-of-00007.safetensors",
23
+ "model.layers.10.feed_forward.w1.weight": "model-00003-of-00007.safetensors",
24
+ "model.layers.10.feed_forward.w2.weight": "model-00003-of-00007.safetensors",
25
+ "model.layers.10.feed_forward.w3.weight": "model-00003-of-00007.safetensors",
26
+ "model.layers.10.ffn_norm.weight": "model-00003-of-00007.safetensors",
27
+ "model.layers.11.attention.wo.weight": "model-00003-of-00007.safetensors",
28
+ "model.layers.11.attention.wqkv.weight": "model-00003-of-00007.safetensors",
29
+ "model.layers.11.attention_norm.weight": "model-00003-of-00007.safetensors",
30
+ "model.layers.11.feed_forward.w1.weight": "model-00003-of-00007.safetensors",
31
+ "model.layers.11.feed_forward.w2.weight": "model-00003-of-00007.safetensors",
32
+ "model.layers.11.feed_forward.w3.weight": "model-00003-of-00007.safetensors",
33
+ "model.layers.11.ffn_norm.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.12.attention.wo.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.12.attention.wqkv.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.12.attention_norm.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.12.feed_forward.w1.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.12.feed_forward.w2.weight": "model-00003-of-00007.safetensors",
39
+ "model.layers.12.feed_forward.w3.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.12.ffn_norm.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.13.attention.wo.weight": "model-00003-of-00007.safetensors",
42
+ "model.layers.13.attention.wqkv.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.13.attention_norm.weight": "model-00003-of-00007.safetensors",
44
+ "model.layers.13.feed_forward.w1.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.13.feed_forward.w2.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.13.feed_forward.w3.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.13.ffn_norm.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.14.attention.wo.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.14.attention.wqkv.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.14.attention_norm.weight": "model-00003-of-00007.safetensors",
51
+ "model.layers.14.feed_forward.w1.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.14.feed_forward.w2.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.14.feed_forward.w3.weight": "model-00003-of-00007.safetensors",
54
+ "model.layers.14.ffn_norm.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.15.attention.wo.weight": "model-00003-of-00007.safetensors",
56
+ "model.layers.15.attention.wqkv.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.15.attention_norm.weight": "model-00004-of-00007.safetensors",
58
+ "model.layers.15.feed_forward.w1.weight": "model-00004-of-00007.safetensors",
59
+ "model.layers.15.feed_forward.w2.weight": "model-00004-of-00007.safetensors",
60
+ "model.layers.15.feed_forward.w3.weight": "model-00004-of-00007.safetensors",
61
+ "model.layers.15.ffn_norm.weight": "model-00004-of-00007.safetensors",
62
+ "model.layers.16.attention.wo.weight": "model-00004-of-00007.safetensors",
63
+ "model.layers.16.attention.wqkv.weight": "model-00004-of-00007.safetensors",
64
+ "model.layers.16.attention_norm.weight": "model-00004-of-00007.safetensors",
65
+ "model.layers.16.feed_forward.w1.weight": "model-00004-of-00007.safetensors",
66
+ "model.layers.16.feed_forward.w2.weight": "model-00004-of-00007.safetensors",
67
+ "model.layers.16.feed_forward.w3.weight": "model-00004-of-00007.safetensors",
68
+ "model.layers.16.ffn_norm.weight": "model-00004-of-00007.safetensors",
69
+ "model.layers.17.attention.wo.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.17.attention.wqkv.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.17.attention_norm.weight": "model-00004-of-00007.safetensors",
72
+ "model.layers.17.feed_forward.w1.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.17.feed_forward.w2.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.17.feed_forward.w3.weight": "model-00004-of-00007.safetensors",
75
+ "model.layers.17.ffn_norm.weight": "model-00004-of-00007.safetensors",
76
+ "model.layers.18.attention.wo.weight": "model-00004-of-00007.safetensors",
77
+ "model.layers.18.attention.wqkv.weight": "model-00004-of-00007.safetensors",
78
+ "model.layers.18.attention_norm.weight": "model-00004-of-00007.safetensors",
79
+ "model.layers.18.feed_forward.w1.weight": "model-00004-of-00007.safetensors",
80
+ "model.layers.18.feed_forward.w2.weight": "model-00004-of-00007.safetensors",
81
+ "model.layers.18.feed_forward.w3.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.18.ffn_norm.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.19.attention.wo.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.19.attention.wqkv.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.19.attention_norm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.19.feed_forward.w1.weight": "model-00004-of-00007.safetensors",
87
+ "model.layers.19.feed_forward.w2.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.19.feed_forward.w3.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.19.ffn_norm.weight": "model-00004-of-00007.safetensors",
90
+ "model.layers.2.attention.wo.weight": "model-00001-of-00007.safetensors",
91
+ "model.layers.2.attention.wqkv.weight": "model-00001-of-00007.safetensors",
92
+ "model.layers.2.attention_norm.weight": "model-00001-of-00007.safetensors",
93
+ "model.layers.2.feed_forward.w1.weight": "model-00001-of-00007.safetensors",
94
+ "model.layers.2.feed_forward.w2.weight": "model-00001-of-00007.safetensors",
95
+ "model.layers.2.feed_forward.w3.weight": "model-00001-of-00007.safetensors",
96
+ "model.layers.2.ffn_norm.weight": "model-00001-of-00007.safetensors",
97
+ "model.layers.20.attention.wo.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.20.attention.wqkv.weight": "model-00004-of-00007.safetensors",
99
+ "model.layers.20.attention_norm.weight": "model-00005-of-00007.safetensors",
100
+ "model.layers.20.feed_forward.w1.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.20.feed_forward.w2.weight": "model-00005-of-00007.safetensors",
102
+ "model.layers.20.feed_forward.w3.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.20.ffn_norm.weight": "model-00005-of-00007.safetensors",
104
+ "model.layers.21.attention.wo.weight": "model-00005-of-00007.safetensors",
105
+ "model.layers.21.attention.wqkv.weight": "model-00005-of-00007.safetensors",
106
+ "model.layers.21.attention_norm.weight": "model-00005-of-00007.safetensors",
107
+ "model.layers.21.feed_forward.w1.weight": "model-00005-of-00007.safetensors",
108
+ "model.layers.21.feed_forward.w2.weight": "model-00005-of-00007.safetensors",
109
+ "model.layers.21.feed_forward.w3.weight": "model-00005-of-00007.safetensors",
110
+ "model.layers.21.ffn_norm.weight": "model-00005-of-00007.safetensors",
111
+ "model.layers.22.attention.wo.weight": "model-00005-of-00007.safetensors",
112
+ "model.layers.22.attention.wqkv.weight": "model-00005-of-00007.safetensors",
113
+ "model.layers.22.attention_norm.weight": "model-00005-of-00007.safetensors",
114
+ "model.layers.22.feed_forward.w1.weight": "model-00005-of-00007.safetensors",
115
+ "model.layers.22.feed_forward.w2.weight": "model-00005-of-00007.safetensors",
116
+ "model.layers.22.feed_forward.w3.weight": "model-00005-of-00007.safetensors",
117
+ "model.layers.22.ffn_norm.weight": "model-00005-of-00007.safetensors",
118
+ "model.layers.23.attention.wo.weight": "model-00005-of-00007.safetensors",
119
+ "model.layers.23.attention.wqkv.weight": "model-00005-of-00007.safetensors",
120
+ "model.layers.23.attention_norm.weight": "model-00005-of-00007.safetensors",
121
+ "model.layers.23.feed_forward.w1.weight": "model-00005-of-00007.safetensors",
122
+ "model.layers.23.feed_forward.w2.weight": "model-00005-of-00007.safetensors",
123
+ "model.layers.23.feed_forward.w3.weight": "model-00005-of-00007.safetensors",
124
+ "model.layers.23.ffn_norm.weight": "model-00005-of-00007.safetensors",
125
+ "model.layers.24.attention.wo.weight": "model-00005-of-00007.safetensors",
126
+ "model.layers.24.attention.wqkv.weight": "model-00005-of-00007.safetensors",
127
+ "model.layers.24.attention_norm.weight": "model-00005-of-00007.safetensors",
128
+ "model.layers.24.feed_forward.w1.weight": "model-00005-of-00007.safetensors",
129
+ "model.layers.24.feed_forward.w2.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.24.feed_forward.w3.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.24.ffn_norm.weight": "model-00005-of-00007.safetensors",
132
+ "model.layers.25.attention.wo.weight": "model-00005-of-00007.safetensors",
133
+ "model.layers.25.attention.wqkv.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.25.attention_norm.weight": "model-00005-of-00007.safetensors",
135
+ "model.layers.25.feed_forward.w1.weight": "model-00005-of-00007.safetensors",
136
+ "model.layers.25.feed_forward.w2.weight": "model-00005-of-00007.safetensors",
137
+ "model.layers.25.feed_forward.w3.weight": "model-00005-of-00007.safetensors",
138
+ "model.layers.25.ffn_norm.weight": "model-00005-of-00007.safetensors",
139
+ "model.layers.26.attention.wo.weight": "model-00005-of-00007.safetensors",
140
+ "model.layers.26.attention.wqkv.weight": "model-00005-of-00007.safetensors",
141
+ "model.layers.26.attention_norm.weight": "model-00006-of-00007.safetensors",
142
+ "model.layers.26.feed_forward.w1.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.26.feed_forward.w2.weight": "model-00006-of-00007.safetensors",
144
+ "model.layers.26.feed_forward.w3.weight": "model-00006-of-00007.safetensors",
145
+ "model.layers.26.ffn_norm.weight": "model-00006-of-00007.safetensors",
146
+ "model.layers.27.attention.wo.weight": "model-00006-of-00007.safetensors",
147
+ "model.layers.27.attention.wqkv.weight": "model-00006-of-00007.safetensors",
148
+ "model.layers.27.attention_norm.weight": "model-00006-of-00007.safetensors",
149
+ "model.layers.27.feed_forward.w1.weight": "model-00006-of-00007.safetensors",
150
+ "model.layers.27.feed_forward.w2.weight": "model-00006-of-00007.safetensors",
151
+ "model.layers.27.feed_forward.w3.weight": "model-00006-of-00007.safetensors",
152
+ "model.layers.27.ffn_norm.weight": "model-00006-of-00007.safetensors",
153
+ "model.layers.28.attention.wo.weight": "model-00006-of-00007.safetensors",
154
+ "model.layers.28.attention.wqkv.weight": "model-00006-of-00007.safetensors",
155
+ "model.layers.28.attention_norm.weight": "model-00006-of-00007.safetensors",
156
+ "model.layers.28.feed_forward.w1.weight": "model-00006-of-00007.safetensors",
157
+ "model.layers.28.feed_forward.w2.weight": "model-00006-of-00007.safetensors",
158
+ "model.layers.28.feed_forward.w3.weight": "model-00006-of-00007.safetensors",
159
+ "model.layers.28.ffn_norm.weight": "model-00006-of-00007.safetensors",
160
+ "model.layers.29.attention.wo.weight": "model-00006-of-00007.safetensors",
161
+ "model.layers.29.attention.wqkv.weight": "model-00006-of-00007.safetensors",
162
+ "model.layers.29.attention_norm.weight": "model-00006-of-00007.safetensors",
163
+ "model.layers.29.feed_forward.w1.weight": "model-00006-of-00007.safetensors",
164
+ "model.layers.29.feed_forward.w2.weight": "model-00006-of-00007.safetensors",
165
+ "model.layers.29.feed_forward.w3.weight": "model-00006-of-00007.safetensors",
166
+ "model.layers.29.ffn_norm.weight": "model-00006-of-00007.safetensors",
167
+ "model.layers.3.attention.wo.weight": "model-00001-of-00007.safetensors",
168
+ "model.layers.3.attention.wqkv.weight": "model-00001-of-00007.safetensors",
169
+ "model.layers.3.attention_norm.weight": "model-00002-of-00007.safetensors",
170
+ "model.layers.3.feed_forward.w1.weight": "model-00001-of-00007.safetensors",
171
+ "model.layers.3.feed_forward.w2.weight": "model-00002-of-00007.safetensors",
172
+ "model.layers.3.feed_forward.w3.weight": "model-00001-of-00007.safetensors",
173
+ "model.layers.3.ffn_norm.weight": "model-00002-of-00007.safetensors",
174
+ "model.layers.30.attention.wo.weight": "model-00006-of-00007.safetensors",
175
+ "model.layers.30.attention.wqkv.weight": "model-00006-of-00007.safetensors",
176
+ "model.layers.30.attention_norm.weight": "model-00006-of-00007.safetensors",
177
+ "model.layers.30.feed_forward.w1.weight": "model-00006-of-00007.safetensors",
178
+ "model.layers.30.feed_forward.w2.weight": "model-00006-of-00007.safetensors",
179
+ "model.layers.30.feed_forward.w3.weight": "model-00006-of-00007.safetensors",
180
+ "model.layers.30.ffn_norm.weight": "model-00006-of-00007.safetensors",
181
+ "model.layers.31.attention.wo.weight": "model-00006-of-00007.safetensors",
182
+ "model.layers.31.attention.wqkv.weight": "model-00006-of-00007.safetensors",
183
+ "model.layers.31.attention_norm.weight": "model-00006-of-00007.safetensors",
184
+ "model.layers.31.feed_forward.w1.weight": "model-00006-of-00007.safetensors",
185
+ "model.layers.31.feed_forward.w2.weight": "model-00006-of-00007.safetensors",
186
+ "model.layers.31.feed_forward.w3.weight": "model-00006-of-00007.safetensors",
187
+ "model.layers.31.ffn_norm.weight": "model-00006-of-00007.safetensors",
188
+ "model.layers.4.attention.wo.weight": "model-00002-of-00007.safetensors",
189
+ "model.layers.4.attention.wqkv.weight": "model-00002-of-00007.safetensors",
190
+ "model.layers.4.attention_norm.weight": "model-00002-of-00007.safetensors",
191
+ "model.layers.4.feed_forward.w1.weight": "model-00002-of-00007.safetensors",
192
+ "model.layers.4.feed_forward.w2.weight": "model-00002-of-00007.safetensors",
193
+ "model.layers.4.feed_forward.w3.weight": "model-00002-of-00007.safetensors",
194
+ "model.layers.4.ffn_norm.weight": "model-00002-of-00007.safetensors",
195
+ "model.layers.5.attention.wo.weight": "model-00002-of-00007.safetensors",
196
+ "model.layers.5.attention.wqkv.weight": "model-00002-of-00007.safetensors",
197
+ "model.layers.5.attention_norm.weight": "model-00002-of-00007.safetensors",
198
+ "model.layers.5.feed_forward.w1.weight": "model-00002-of-00007.safetensors",
199
+ "model.layers.5.feed_forward.w2.weight": "model-00002-of-00007.safetensors",
200
+ "model.layers.5.feed_forward.w3.weight": "model-00002-of-00007.safetensors",
201
+ "model.layers.5.ffn_norm.weight": "model-00002-of-00007.safetensors",
202
+ "model.layers.6.attention.wo.weight": "model-00002-of-00007.safetensors",
203
+ "model.layers.6.attention.wqkv.weight": "model-00002-of-00007.safetensors",
204
+ "model.layers.6.attention_norm.weight": "model-00002-of-00007.safetensors",
205
+ "model.layers.6.feed_forward.w1.weight": "model-00002-of-00007.safetensors",
206
+ "model.layers.6.feed_forward.w2.weight": "model-00002-of-00007.safetensors",
207
+ "model.layers.6.feed_forward.w3.weight": "model-00002-of-00007.safetensors",
208
+ "model.layers.6.ffn_norm.weight": "model-00002-of-00007.safetensors",
209
+ "model.layers.7.attention.wo.weight": "model-00002-of-00007.safetensors",
210
+ "model.layers.7.attention.wqkv.weight": "model-00002-of-00007.safetensors",
211
+ "model.layers.7.attention_norm.weight": "model-00002-of-00007.safetensors",
212
+ "model.layers.7.feed_forward.w1.weight": "model-00002-of-00007.safetensors",
213
+ "model.layers.7.feed_forward.w2.weight": "model-00002-of-00007.safetensors",
214
+ "model.layers.7.feed_forward.w3.weight": "model-00002-of-00007.safetensors",
215
+ "model.layers.7.ffn_norm.weight": "model-00002-of-00007.safetensors",
216
+ "model.layers.8.attention.wo.weight": "model-00002-of-00007.safetensors",
217
+ "model.layers.8.attention.wqkv.weight": "model-00002-of-00007.safetensors",
218
+ "model.layers.8.attention_norm.weight": "model-00002-of-00007.safetensors",
219
+ "model.layers.8.feed_forward.w1.weight": "model-00002-of-00007.safetensors",
220
+ "model.layers.8.feed_forward.w2.weight": "model-00002-of-00007.safetensors",
221
+ "model.layers.8.feed_forward.w3.weight": "model-00002-of-00007.safetensors",
222
+ "model.layers.8.ffn_norm.weight": "model-00002-of-00007.safetensors",
223
+ "model.layers.9.attention.wo.weight": "model-00002-of-00007.safetensors",
224
+ "model.layers.9.attention.wqkv.weight": "model-00002-of-00007.safetensors",
225
+ "model.layers.9.attention_norm.weight": "model-00003-of-00007.safetensors",
226
+ "model.layers.9.feed_forward.w1.weight": "model-00002-of-00007.safetensors",
227
+ "model.layers.9.feed_forward.w2.weight": "model-00003-of-00007.safetensors",
228
+ "model.layers.9.feed_forward.w3.weight": "model-00003-of-00007.safetensors",
229
+ "model.layers.9.ffn_norm.weight": "model-00003-of-00007.safetensors",
230
+ "model.norm.weight": "model-00006-of-00007.safetensors",
231
+ "model.output.weight": "model-00007-of-00007.safetensors",
232
+ "model.tok_embeddings.weight": "model-00001-of-00007.safetensors",
233
+ "output.weight": "model-00007-of-00007.safetensors"
234
+ }
235
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "</s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "<unk>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff