Hugging Face's logo

Kwaipilot
/
KwaiCoder-23B-A4B-v1

Text Generation
Transformers
Safetensors
multilingual
mixtral
code-generation
text-generation-inference
Model card Files Community
2
songhuan03 commited on
Commit
ed694fc
·
1 Parent(s): a7dcc11

init commit

Browse files
Files changed (25) hide show
  1. config.json +33 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00019.safetensors +3 -0
  4. model-00002-of-00019.safetensors +3 -0
  5. model-00003-of-00019.safetensors +3 -0
  6. model-00004-of-00019.safetensors +3 -0
  7. model-00005-of-00019.safetensors +3 -0
  8. model-00006-of-00019.safetensors +3 -0
  9. model-00007-of-00019.safetensors +3 -0
  10. model-00008-of-00019.safetensors +3 -0
  11. model-00009-of-00019.safetensors +3 -0
  12. model-00010-of-00019.safetensors +3 -0
  13. model-00011-of-00019.safetensors +3 -0
  14. model-00012-of-00019.safetensors +3 -0
  15. model-00013-of-00019.safetensors +3 -0
  16. model-00014-of-00019.safetensors +3 -0
  17. model-00015-of-00019.safetensors +3 -0
  18. model-00016-of-00019.safetensors +3 -0
  19. model-00017-of-00019.safetensors +3 -0
  20. model-00018-of-00019.safetensors +3 -0
  21. model-00019-of-00019.safetensors +3 -0
  22. model.safetensors.index.json +0 -0
  23. special_tokens_map.json +23 -0
  24. tokenizer.json +0 -0
  25. tokenizer_config.json +194 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/share/songhuan03/NeMo-Framework-Launcher/launcher_scripts/results/mixtral_64e_a4b_ds/results/megatron_mixtral-step=1000-hf",
3
+ "activation": "silu",
4
+ "architectures": [
5
+ "MixtralForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32014,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1376,
15
+ "max_position_embeddings": 4096,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 32,
18
+ "num_experts_per_tok": 8,
19
+ "num_hidden_layers": 20,
20
+ "num_key_value_heads": 32,
21
+ "num_local_experts": 64,
22
+ "output_router_logits": false,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_theta": 100000.0,
25
+ "router_aux_loss_coef": 0.02,
26
+ "router_jitter_noise": 0.0,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.47.0",
31
+ "use_cache": true,
32
+ "vocab_size": 32128
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32013,
4
+ "eos_token_id": 32014,
5
+ "transformers_version": "4.47.0"
6
+ }
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0935408481bf83a151afb27103f27a9141d6f18aab3c7b4212d8f84a959311fe
3
+ size 4989149432
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b45737933889fe24507dcf889bae40a8e577fcfa81c2236a1a514b0dcd22d9
3
+ size 4934691224
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7493a4be1d93e2ecc510fdd712ef9e354bba5fe6fefa13917e89ebd79d4e0be7
3
+ size 4981845064
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f2b505ab19b16de888ba7ebaa6a740ab84dfb7a607015512bf143ec867de27
3
+ size 4981320928
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f398e3dc13b51ebdb7d0d5fd45a9de041b4dad7737e61cbcfce6b4360fde357
3
+ size 4981320944
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02957ce9e3af321352554d0ca5e290c41b88f132d42cfba85dd32748ee3839e
3
+ size 4981320944
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67125ab235625185b724579ba69fcca14c2c02079a346a9a14b1cbf68d2a4c45
3
+ size 4981320944
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f511a81a213ccb7f1d2d02bf5ed1b3ce7ba7c36266cb804efde021515d8efeb
3
+ size 4981320944
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a97eb7971b0187c6afef4f1ffaa9e5e87404534751ffa7554bce38d1e58238f
3
+ size 4981320944
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e98dbcd202e5d2403dbfe12e88d45a5ba1d22f3d06af657a369d06d641ef83
3
+ size 4981321088
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355d5dde7a7aabf8f470eebdd2435b0027a2db5cad5406a9f5d579a4ad594b01
3
+ size 4981321160
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fd6b7dfa864360c9ffa379aed0b80a477a83e26648780dc69b788e354ff548
3
+ size 4981321160
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3df40b06112c43cf69191f58f387000acfac033ab8b047939e25f109f69be94
3
+ size 4981321160
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a940fd494db6a9775a76be174ed9e936c917afa3635f57a60b43f907c1b1b02
3
+ size 4979780464
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0a0159c505d0f6cf86e5fdffa2614974e2d081984eea359d0a7eb77de9dbc5
3
+ size 4981845280
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86a6c704cf67db7f55fcaccf4649c61942f664523e548728c2abf6612de5663
3
+ size 4981321144
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb8aadd16f650c172e20d0ad2ec63bdbd3565523cc2d220f85bdf5f1b04f6e0
3
+ size 4981321160
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b851b1e35e9771235f7a68fc1f3718e0d885149a20953ab2d6f5dd71344362
3
+ size 4981321160
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7cf4555b5f7efea27f5dcb240460ed5684bf2620b731eb1d64a87014288b3e
3
+ size 3389588112
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "32000": {
7
+ "content": "õ",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "32001": {
15
+ "content": "÷",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "32002": {
23
+ "content": "Á",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32003": {
31
+ "content": "ý",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "32004": {
39
+ "content": "À",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "32005": {
47
+ "content": "ÿ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "32006": {
55
+ "content": "ø",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "32007": {
63
+ "content": "ú",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "32008": {
71
+ "content": "þ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "32009": {
79
+ "content": "ü",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "32010": {
87
+ "content": "ù",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "32011": {
95
+ "content": "ö",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "32012": {
103
+ "content": "û",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "32013": {
111
+ "content": "<｜begin▁of▁sentence｜>",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32014": {
119
+ "content": "<｜end▁of▁sentence｜>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32015": {
127
+ "content": "<｜fim▁hole｜>",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "32016": {
135
+ "content": "<｜fim▁begin｜>",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "32017": {
143
+ "content": "<｜fim▁end｜>",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "32018": {
151
+ "content": "<pad>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "32019": {
159
+ "content": "<|User|>",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "32020": {
167
+ "content": "<|Assistant|>",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "32021": {
175
+ "content": "<|EOT|>",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<｜end▁of▁sentence｜>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizer",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }