ZwwWayne commited on
Commit
aa1fc6c
1 Parent(s): 5b50661

update model weights

Browse files
.gitattributes CHANGED
@@ -43,3 +43,11 @@ pytorch_model-00001-of-00008.bin filter=lfs diff=lfs merge=lfs -text
43
  pytorch_model-00002-of-00008.bin filter=lfs diff=lfs merge=lfs -text
44
  pytorch_model-00005-of-00008.bin filter=lfs diff=lfs merge=lfs -text
45
  pytorch_model.bin.index.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
43
  pytorch_model-00002-of-00008.bin filter=lfs diff=lfs merge=lfs -text
44
  pytorch_model-00005-of-00008.bin filter=lfs diff=lfs merge=lfs -text
45
  pytorch_model.bin.index.json filter=lfs diff=lfs merge=lfs -text
46
+ model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
47
+ model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
48
+ model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
49
+ model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
50
+ model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
51
+ model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
52
+ model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
53
+ model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -2,6 +2,7 @@
2
  "architectures": [
3
  "InternLM2ForCausalLM"
4
  ],
 
5
  "auto_map": {
6
  "AutoConfig": "configuration_internlm2.InternLM2Config",
7
  "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
@@ -21,14 +22,11 @@
21
  "num_key_value_heads": 8,
22
  "pad_token_id": 2,
23
  "rms_norm_eps": 1e-05,
24
- "rope_scaling": {
25
- "factor": 2.0,
26
- "type": "dynamic"
27
- },
28
  "rope_theta": 1000000,
29
  "tie_word_embeddings": false,
30
- "torch_dtype": "float16",
31
- "transformers_version": "4.33.2",
32
  "use_cache": true,
33
  "vocab_size": 92544
34
  }
 
2
  "architectures": [
3
  "InternLM2ForCausalLM"
4
  ],
5
+ "attn_implementation": "eager",
6
  "auto_map": {
7
  "AutoConfig": "configuration_internlm2.InternLM2Config",
8
  "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
 
22
  "num_key_value_heads": 8,
23
  "pad_token_id": 2,
24
  "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
 
 
 
26
  "rope_theta": 1000000,
27
  "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.37.1",
30
  "use_cache": true,
31
  "vocab_size": 92544
32
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 2,
6
- "transformers_version": "4.33.2"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 2,
6
+ "transformers_version": "4.37.1"
7
  }
pytorch_model-00001-of-00008.bin → model-00001-of-00008.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdd03c1ea040b17ce992eb303d0824f5694932902d0c3fa57b5a8d1df2dc8082
3
- size 1949342053
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cec9c25c5f54c545deb16123fc72a0b265fd6bed4c467b4519380a8b215b62b
3
+ size 1949337704
pytorch_model-00002-of-00008.bin → model-00002-of-00008.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:377d66327bcc2dc4b3e5f4e90f24b428c55832ece07194990248647ea65c2db5
3
- size 1946249825
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4735b4b15a670c33a6aefe70cf39e4ba08468a496167b5233fa43ebcfbd42895
3
+ size 1946242696
pytorch_model-00003-of-00008.bin → model-00003-of-00008.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98aa01b7ffd7901699b4588b5e6b8f753e66c1874f8b855c36b23de2c95ae9d8
3
- size 1979786923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523c7292140bc4c37d5fbd517ec7f9d0aa27b7d22822fdfc730f94f3bf02ebac
3
+ size 1979780440
pytorch_model-00004-of-00008.bin → model-00004-of-00008.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9362abdb2afd077e579a7860ad570769255c2d64af2b0831413578c77a44d779
3
- size 1946249889
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd631ca87a5e516780832e747156e304a3c9bb53f85c4304550bff970d2db26
3
+ size 1946242728
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a28f7db7ba9fc0991e3552a156e11b942494e945c4c134003aad40bb4e49ed6
3
+ size 1979780456
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d330d795037a2db1c7a15a991c88ba6bf2bc2890e36210571d7499d1ae6dfd51
3
+ size 1946242728
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c65720f77de3aec168dff5b0f11e779f4c9059f2fdb04c67bae4321f5efd6a
3
+ size 1979780456
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb488551289c4630b7b1fb015acf2ff52a206383c96370a7664b42253a007eae
3
+ size 1748035640
model.safetensors.index.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15475417088
4
+ },
5
+ "weight_map": {
6
+ "model.layers.0.attention.wo.weight": "model-00001-of-00008.safetensors",
7
+ "model.layers.0.attention.wqkv.weight": "model-00001-of-00008.safetensors",
8
+ "model.layers.0.attention_norm.weight": "model-00001-of-00008.safetensors",
9
+ "model.layers.0.feed_forward.w1.weight": "model-00001-of-00008.safetensors",
10
+ "model.layers.0.feed_forward.w2.weight": "model-00001-of-00008.safetensors",
11
+ "model.layers.0.feed_forward.w3.weight": "model-00001-of-00008.safetensors",
12
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00008.safetensors",
13
+ "model.layers.1.attention.wo.weight": "model-00001-of-00008.safetensors",
14
+ "model.layers.1.attention.wqkv.weight": "model-00001-of-00008.safetensors",
15
+ "model.layers.1.attention_norm.weight": "model-00001-of-00008.safetensors",
16
+ "model.layers.1.feed_forward.w1.weight": "model-00001-of-00008.safetensors",
17
+ "model.layers.1.feed_forward.w2.weight": "model-00001-of-00008.safetensors",
18
+ "model.layers.1.feed_forward.w3.weight": "model-00001-of-00008.safetensors",
19
+ "model.layers.1.ffn_norm.weight": "model-00001-of-00008.safetensors",
20
+ "model.layers.10.attention.wo.weight": "model-00003-of-00008.safetensors",
21
+ "model.layers.10.attention.wqkv.weight": "model-00003-of-00008.safetensors",
22
+ "model.layers.10.attention_norm.weight": "model-00003-of-00008.safetensors",
23
+ "model.layers.10.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
24
+ "model.layers.10.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
25
+ "model.layers.10.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
26
+ "model.layers.10.ffn_norm.weight": "model-00003-of-00008.safetensors",
27
+ "model.layers.11.attention.wo.weight": "model-00003-of-00008.safetensors",
28
+ "model.layers.11.attention.wqkv.weight": "model-00003-of-00008.safetensors",
29
+ "model.layers.11.attention_norm.weight": "model-00004-of-00008.safetensors",
30
+ "model.layers.11.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
31
+ "model.layers.11.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
32
+ "model.layers.11.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
33
+ "model.layers.11.ffn_norm.weight": "model-00004-of-00008.safetensors",
34
+ "model.layers.12.attention.wo.weight": "model-00004-of-00008.safetensors",
35
+ "model.layers.12.attention.wqkv.weight": "model-00004-of-00008.safetensors",
36
+ "model.layers.12.attention_norm.weight": "model-00004-of-00008.safetensors",
37
+ "model.layers.12.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
38
+ "model.layers.12.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
39
+ "model.layers.12.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
40
+ "model.layers.12.ffn_norm.weight": "model-00004-of-00008.safetensors",
41
+ "model.layers.13.attention.wo.weight": "model-00004-of-00008.safetensors",
42
+ "model.layers.13.attention.wqkv.weight": "model-00004-of-00008.safetensors",
43
+ "model.layers.13.attention_norm.weight": "model-00004-of-00008.safetensors",
44
+ "model.layers.13.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
45
+ "model.layers.13.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
46
+ "model.layers.13.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
47
+ "model.layers.13.ffn_norm.weight": "model-00004-of-00008.safetensors",
48
+ "model.layers.14.attention.wo.weight": "model-00004-of-00008.safetensors",
49
+ "model.layers.14.attention.wqkv.weight": "model-00004-of-00008.safetensors",
50
+ "model.layers.14.attention_norm.weight": "model-00004-of-00008.safetensors",
51
+ "model.layers.14.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
52
+ "model.layers.14.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
53
+ "model.layers.14.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
54
+ "model.layers.14.ffn_norm.weight": "model-00004-of-00008.safetensors",
55
+ "model.layers.15.attention.wo.weight": "model-00004-of-00008.safetensors",
56
+ "model.layers.15.attention.wqkv.weight": "model-00004-of-00008.safetensors",
57
+ "model.layers.15.attention_norm.weight": "model-00004-of-00008.safetensors",
58
+ "model.layers.15.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
59
+ "model.layers.15.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
60
+ "model.layers.15.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
61
+ "model.layers.15.ffn_norm.weight": "model-00004-of-00008.safetensors",
62
+ "model.layers.16.attention.wo.weight": "model-00004-of-00008.safetensors",
63
+ "model.layers.16.attention.wqkv.weight": "model-00004-of-00008.safetensors",
64
+ "model.layers.16.attention_norm.weight": "model-00005-of-00008.safetensors",
65
+ "model.layers.16.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
66
+ "model.layers.16.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
67
+ "model.layers.16.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
68
+ "model.layers.16.ffn_norm.weight": "model-00005-of-00008.safetensors",
69
+ "model.layers.17.attention.wo.weight": "model-00005-of-00008.safetensors",
70
+ "model.layers.17.attention.wqkv.weight": "model-00005-of-00008.safetensors",
71
+ "model.layers.17.attention_norm.weight": "model-00005-of-00008.safetensors",
72
+ "model.layers.17.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
73
+ "model.layers.17.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
74
+ "model.layers.17.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
75
+ "model.layers.17.ffn_norm.weight": "model-00005-of-00008.safetensors",
76
+ "model.layers.18.attention.wo.weight": "model-00005-of-00008.safetensors",
77
+ "model.layers.18.attention.wqkv.weight": "model-00005-of-00008.safetensors",
78
+ "model.layers.18.attention_norm.weight": "model-00005-of-00008.safetensors",
79
+ "model.layers.18.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
80
+ "model.layers.18.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
81
+ "model.layers.18.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
82
+ "model.layers.18.ffn_norm.weight": "model-00005-of-00008.safetensors",
83
+ "model.layers.19.attention.wo.weight": "model-00005-of-00008.safetensors",
84
+ "model.layers.19.attention.wqkv.weight": "model-00005-of-00008.safetensors",
85
+ "model.layers.19.attention_norm.weight": "model-00005-of-00008.safetensors",
86
+ "model.layers.19.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
87
+ "model.layers.19.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
88
+ "model.layers.19.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
89
+ "model.layers.19.ffn_norm.weight": "model-00005-of-00008.safetensors",
90
+ "model.layers.2.attention.wo.weight": "model-00001-of-00008.safetensors",
91
+ "model.layers.2.attention.wqkv.weight": "model-00001-of-00008.safetensors",
92
+ "model.layers.2.attention_norm.weight": "model-00002-of-00008.safetensors",
93
+ "model.layers.2.feed_forward.w1.weight": "model-00001-of-00008.safetensors",
94
+ "model.layers.2.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
95
+ "model.layers.2.feed_forward.w3.weight": "model-00001-of-00008.safetensors",
96
+ "model.layers.2.ffn_norm.weight": "model-00002-of-00008.safetensors",
97
+ "model.layers.20.attention.wo.weight": "model-00005-of-00008.safetensors",
98
+ "model.layers.20.attention.wqkv.weight": "model-00005-of-00008.safetensors",
99
+ "model.layers.20.attention_norm.weight": "model-00006-of-00008.safetensors",
100
+ "model.layers.20.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
101
+ "model.layers.20.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
102
+ "model.layers.20.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
103
+ "model.layers.20.ffn_norm.weight": "model-00006-of-00008.safetensors",
104
+ "model.layers.21.attention.wo.weight": "model-00006-of-00008.safetensors",
105
+ "model.layers.21.attention.wqkv.weight": "model-00006-of-00008.safetensors",
106
+ "model.layers.21.attention_norm.weight": "model-00006-of-00008.safetensors",
107
+ "model.layers.21.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
108
+ "model.layers.21.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
109
+ "model.layers.21.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
110
+ "model.layers.21.ffn_norm.weight": "model-00006-of-00008.safetensors",
111
+ "model.layers.22.attention.wo.weight": "model-00006-of-00008.safetensors",
112
+ "model.layers.22.attention.wqkv.weight": "model-00006-of-00008.safetensors",
113
+ "model.layers.22.attention_norm.weight": "model-00006-of-00008.safetensors",
114
+ "model.layers.22.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
115
+ "model.layers.22.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
116
+ "model.layers.22.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
117
+ "model.layers.22.ffn_norm.weight": "model-00006-of-00008.safetensors",
118
+ "model.layers.23.attention.wo.weight": "model-00006-of-00008.safetensors",
119
+ "model.layers.23.attention.wqkv.weight": "model-00006-of-00008.safetensors",
120
+ "model.layers.23.attention_norm.weight": "model-00006-of-00008.safetensors",
121
+ "model.layers.23.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
122
+ "model.layers.23.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
123
+ "model.layers.23.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
124
+ "model.layers.23.ffn_norm.weight": "model-00006-of-00008.safetensors",
125
+ "model.layers.24.attention.wo.weight": "model-00006-of-00008.safetensors",
126
+ "model.layers.24.attention.wqkv.weight": "model-00006-of-00008.safetensors",
127
+ "model.layers.24.attention_norm.weight": "model-00006-of-00008.safetensors",
128
+ "model.layers.24.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
129
+ "model.layers.24.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
130
+ "model.layers.24.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
131
+ "model.layers.24.ffn_norm.weight": "model-00006-of-00008.safetensors",
132
+ "model.layers.25.attention.wo.weight": "model-00006-of-00008.safetensors",
133
+ "model.layers.25.attention.wqkv.weight": "model-00006-of-00008.safetensors",
134
+ "model.layers.25.attention_norm.weight": "model-00007-of-00008.safetensors",
135
+ "model.layers.25.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
136
+ "model.layers.25.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
137
+ "model.layers.25.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
138
+ "model.layers.25.ffn_norm.weight": "model-00007-of-00008.safetensors",
139
+ "model.layers.26.attention.wo.weight": "model-00007-of-00008.safetensors",
140
+ "model.layers.26.attention.wqkv.weight": "model-00007-of-00008.safetensors",
141
+ "model.layers.26.attention_norm.weight": "model-00007-of-00008.safetensors",
142
+ "model.layers.26.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
143
+ "model.layers.26.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
144
+ "model.layers.26.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
145
+ "model.layers.26.ffn_norm.weight": "model-00007-of-00008.safetensors",
146
+ "model.layers.27.attention.wo.weight": "model-00007-of-00008.safetensors",
147
+ "model.layers.27.attention.wqkv.weight": "model-00007-of-00008.safetensors",
148
+ "model.layers.27.attention_norm.weight": "model-00007-of-00008.safetensors",
149
+ "model.layers.27.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
150
+ "model.layers.27.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
151
+ "model.layers.27.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
152
+ "model.layers.27.ffn_norm.weight": "model-00007-of-00008.safetensors",
153
+ "model.layers.28.attention.wo.weight": "model-00007-of-00008.safetensors",
154
+ "model.layers.28.attention.wqkv.weight": "model-00007-of-00008.safetensors",
155
+ "model.layers.28.attention_norm.weight": "model-00007-of-00008.safetensors",
156
+ "model.layers.28.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
157
+ "model.layers.28.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
158
+ "model.layers.28.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
159
+ "model.layers.28.ffn_norm.weight": "model-00007-of-00008.safetensors",
160
+ "model.layers.29.attention.wo.weight": "model-00007-of-00008.safetensors",
161
+ "model.layers.29.attention.wqkv.weight": "model-00007-of-00008.safetensors",
162
+ "model.layers.29.attention_norm.weight": "model-00008-of-00008.safetensors",
163
+ "model.layers.29.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
164
+ "model.layers.29.feed_forward.w2.weight": "model-00008-of-00008.safetensors",
165
+ "model.layers.29.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
166
+ "model.layers.29.ffn_norm.weight": "model-00008-of-00008.safetensors",
167
+ "model.layers.3.attention.wo.weight": "model-00002-of-00008.safetensors",
168
+ "model.layers.3.attention.wqkv.weight": "model-00002-of-00008.safetensors",
169
+ "model.layers.3.attention_norm.weight": "model-00002-of-00008.safetensors",
170
+ "model.layers.3.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
171
+ "model.layers.3.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
172
+ "model.layers.3.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
173
+ "model.layers.3.ffn_norm.weight": "model-00002-of-00008.safetensors",
174
+ "model.layers.30.attention.wo.weight": "model-00008-of-00008.safetensors",
175
+ "model.layers.30.attention.wqkv.weight": "model-00008-of-00008.safetensors",
176
+ "model.layers.30.attention_norm.weight": "model-00008-of-00008.safetensors",
177
+ "model.layers.30.feed_forward.w1.weight": "model-00008-of-00008.safetensors",
178
+ "model.layers.30.feed_forward.w2.weight": "model-00008-of-00008.safetensors",
179
+ "model.layers.30.feed_forward.w3.weight": "model-00008-of-00008.safetensors",
180
+ "model.layers.30.ffn_norm.weight": "model-00008-of-00008.safetensors",
181
+ "model.layers.31.attention.wo.weight": "model-00008-of-00008.safetensors",
182
+ "model.layers.31.attention.wqkv.weight": "model-00008-of-00008.safetensors",
183
+ "model.layers.31.attention_norm.weight": "model-00008-of-00008.safetensors",
184
+ "model.layers.31.feed_forward.w1.weight": "model-00008-of-00008.safetensors",
185
+ "model.layers.31.feed_forward.w2.weight": "model-00008-of-00008.safetensors",
186
+ "model.layers.31.feed_forward.w3.weight": "model-00008-of-00008.safetensors",
187
+ "model.layers.31.ffn_norm.weight": "model-00008-of-00008.safetensors",
188
+ "model.layers.4.attention.wo.weight": "model-00002-of-00008.safetensors",
189
+ "model.layers.4.attention.wqkv.weight": "model-00002-of-00008.safetensors",
190
+ "model.layers.4.attention_norm.weight": "model-00002-of-00008.safetensors",
191
+ "model.layers.4.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
192
+ "model.layers.4.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
193
+ "model.layers.4.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
194
+ "model.layers.4.ffn_norm.weight": "model-00002-of-00008.safetensors",
195
+ "model.layers.5.attention.wo.weight": "model-00002-of-00008.safetensors",
196
+ "model.layers.5.attention.wqkv.weight": "model-00002-of-00008.safetensors",
197
+ "model.layers.5.attention_norm.weight": "model-00002-of-00008.safetensors",
198
+ "model.layers.5.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
199
+ "model.layers.5.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
200
+ "model.layers.5.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
201
+ "model.layers.5.ffn_norm.weight": "model-00002-of-00008.safetensors",
202
+ "model.layers.6.attention.wo.weight": "model-00002-of-00008.safetensors",
203
+ "model.layers.6.attention.wqkv.weight": "model-00002-of-00008.safetensors",
204
+ "model.layers.6.attention_norm.weight": "model-00002-of-00008.safetensors",
205
+ "model.layers.6.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
206
+ "model.layers.6.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
207
+ "model.layers.6.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
208
+ "model.layers.6.ffn_norm.weight": "model-00002-of-00008.safetensors",
209
+ "model.layers.7.attention.wo.weight": "model-00002-of-00008.safetensors",
210
+ "model.layers.7.attention.wqkv.weight": "model-00002-of-00008.safetensors",
211
+ "model.layers.7.attention_norm.weight": "model-00003-of-00008.safetensors",
212
+ "model.layers.7.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
213
+ "model.layers.7.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
214
+ "model.layers.7.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
215
+ "model.layers.7.ffn_norm.weight": "model-00003-of-00008.safetensors",
216
+ "model.layers.8.attention.wo.weight": "model-00003-of-00008.safetensors",
217
+ "model.layers.8.attention.wqkv.weight": "model-00003-of-00008.safetensors",
218
+ "model.layers.8.attention_norm.weight": "model-00003-of-00008.safetensors",
219
+ "model.layers.8.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
220
+ "model.layers.8.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
221
+ "model.layers.8.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
222
+ "model.layers.8.ffn_norm.weight": "model-00003-of-00008.safetensors",
223
+ "model.layers.9.attention.wo.weight": "model-00003-of-00008.safetensors",
224
+ "model.layers.9.attention.wqkv.weight": "model-00003-of-00008.safetensors",
225
+ "model.layers.9.attention_norm.weight": "model-00003-of-00008.safetensors",
226
+ "model.layers.9.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
227
+ "model.layers.9.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
228
+ "model.layers.9.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
229
+ "model.layers.9.ffn_norm.weight": "model-00003-of-00008.safetensors",
230
+ "model.norm.weight": "model-00008-of-00008.safetensors",
231
+ "model.tok_embeddings.weight": "model-00001-of-00008.safetensors",
232
+ "output.weight": "model-00008-of-00008.safetensors"
233
+ }
234
+ }
pytorch_model-00005-of-00008.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:56761cf09eb95e676bce5c1dc53fd4f8c317775d146fe2313dcb7b81c48cfa39
3
- size 1979786987
 
 
 
 
pytorch_model-00006-of-00008.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a825cc1e85ffc038efaed5a06ae398f424916bdd768bcf62d7fb4bc552d71ef
3
- size 1946249889
 
 
 
 
pytorch_model-00007-of-00008.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:224105eee8f19409994aea890cc6cc9da16ef4278ad831fdd4e9fcf86f925256
3
- size 1979786987
 
 
 
 
pytorch_model-00008-of-00008.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ed276d23e8a4ab9ec5bafe491cb7147b4b51232a66ce0b9f304bc8a5430d82f
3
- size 1748039973
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8a1efb6998624330a0564f9bba63eb8ccae0ad54a6d0176c64f2eb30721f2b5
3
- size 18179
 
 
 
 
special_tokens_map.json CHANGED
@@ -7,8 +7,32 @@
7
  "<|interpreter|>",
8
  "<|plugin|>"
9
  ],
10
- "bos_token": "<s>",
11
- "eos_token": "</s>",
12
- "pad_token": "</s>",
13
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
 
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
  }
tokenization_internlm2_fast.py CHANGED
@@ -56,14 +56,14 @@ class InternLM2Converter(SpmConverter):
56
  return unk_id
57
 
58
  def decoder(self, replacement, add_prefix_space):
59
- decoders_sequence = [
60
- decoders.Replace("▁", " "),
61
- decoders.ByteFallback(),
62
- decoders.Fuse(),
63
- ]
64
- if self.proto.normalizer_spec.add_dummy_prefix:
65
- decoders_sequence.append(decoders.Strip(content=" ", left=1))
66
- return decoders.Sequence(decoders_sequence)
67
 
68
  def tokenizer(self, proto):
69
  model_type = proto.trainer_spec.model_type
 
56
  return unk_id
57
 
58
  def decoder(self, replacement, add_prefix_space):
59
+ return decoders.Sequence(
60
+ [
61
+ decoders.Replace("▁", " "),
62
+ decoders.ByteFallback(),
63
+ decoders.Fuse(),
64
+ decoders.Strip(content=" ", left=1),
65
+ ]
66
+ )
67
 
68
  def tokenizer(self, proto):
69
  model_type = proto.trainer_spec.model_type
tokenizer_config.json CHANGED
@@ -1,17 +1,6 @@
1
  {
2
- "auto_map": {
3
- "AutoTokenizer": [
4
- "tokenization_internlm2.InternLM2Tokenizer",
5
- "tokenization_internlm2_fast.InternLM2TokenizerFast"
6
- ]
7
- },
8
- "bos_token": "<s>",
9
- "clean_up_tokenization_spaces": false,
10
- "eos_token": "</s>",
11
- "model_max_length": 1000000000000000019884624838656,
12
- "pad_token": "</s>",
13
- "tokenizer_class": "InternLM2Tokenizer",
14
- "unk_token": "<unk>",
15
  "added_tokens_decoder": {
16
  "0": {
17
  "content": "<unk>",
@@ -37,48 +26,48 @@
37
  "single_word": false,
38
  "special": true
39
  },
40
- "92543": {
41
- "content": "<|im_start|>",
42
  "lstrip": false,
43
  "normalized": false,
44
  "rstrip": false,
45
  "single_word": false,
46
  "special": true
47
  },
48
- "92542": {
49
- "content": "<|im_end|>",
50
  "lstrip": false,
51
  "normalized": false,
52
  "rstrip": false,
53
  "single_word": false,
54
  "special": true
55
  },
56
- "92541": {
57
- "content": "<|action_start|>",
58
  "lstrip": false,
59
  "normalized": false,
60
  "rstrip": false,
61
  "single_word": false,
62
  "special": true
63
  },
64
- "92540": {
65
- "content": "<|action_end|>",
66
  "lstrip": false,
67
  "normalized": false,
68
  "rstrip": false,
69
  "single_word": false,
70
  "special": true
71
  },
72
- "92539": {
73
- "content": "<|interpreter|>",
74
  "lstrip": false,
75
  "normalized": false,
76
  "rstrip": false,
77
  "single_word": false,
78
  "special": true
79
  },
80
- "92538": {
81
- "content": "<|plugin|>",
82
  "lstrip": false,
83
  "normalized": false,
84
  "rstrip": false,
@@ -94,5 +83,20 @@
94
  "<|interpreter|>",
95
  "<|plugin|>"
96
  ],
97
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
98
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
 
 
 
 
 
 
 
 
 
 
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "92538": {
30
+ "content": "<|plugin|>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "92539": {
38
+ "content": "<|interpreter|>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  },
45
+ "92540": {
46
+ "content": "<|action_end|>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": false,
50
  "single_word": false,
51
  "special": true
52
  },
53
+ "92541": {
54
+ "content": "<|action_start|>",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": false,
58
  "single_word": false,
59
  "special": true
60
  },
61
+ "92542": {
62
+ "content": "<|im_end|>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": false,
66
  "single_word": false,
67
  "special": true
68
  },
69
+ "92543": {
70
+ "content": "<|im_start|>",
71
  "lstrip": false,
72
  "normalized": false,
73
  "rstrip": false,
 
83
  "<|interpreter|>",
84
  "<|plugin|>"
85
  ],
86
+ "auto_map": {
87
+ "AutoTokenizer": [
88
+ "tokenization_internlm2.InternLM2Tokenizer",
89
+ "tokenization_internlm2_fast.InternLM2TokenizerFast"
90
+ ]
91
+ },
92
+ "bos_token": "<s>",
93
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
94
+ "clean_up_tokenization_spaces": false,
95
+ "decode_with_prefix_space": false,
96
+ "eos_token": "</s>",
97
+ "model_max_length": 1000000000000000019884624838656,
98
+ "pad_token": "</s>",
99
+ "sp_model_kwargs": null,
100
+ "tokenizer_class": "InternLM2Tokenizer",
101
+ "unk_token": "<unk>"
102
+ }