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
zhangxiaojiang commited on
Commit
18030b7
·
1 Parent(s): ed694fc

bf16 commit

Browse files
Files changed (28) hide show
  1. config.json +2 -3
  2. generation_config.json +1 -1
  3. model-00001-of-00019.safetensors → model-00001-of-00010.safetensors +2 -2
  4. model-00002-of-00019.safetensors → model-00002-of-00010.safetensors +2 -2
  5. model-00003-of-00019.safetensors → model-00003-of-00010.safetensors +2 -2
  6. model-00004-of-00019.safetensors → model-00004-of-00010.safetensors +2 -2
  7. model-00005-of-00010.safetensors +3 -0
  8. model-00005-of-00019.safetensors +0 -3
  9. model-00006-of-00010.safetensors +3 -0
  10. model-00006-of-00019.safetensors +0 -3
  11. model-00007-of-00010.safetensors +3 -0
  12. model-00007-of-00019.safetensors +0 -3
  13. model-00008-of-00010.safetensors +3 -0
  14. model-00008-of-00019.safetensors +0 -3
  15. model-00009-of-00010.safetensors +3 -0
  16. model-00009-of-00019.safetensors +0 -3
  17. model-00010-of-00010.safetensors +3 -0
  18. model-00010-of-00019.safetensors +0 -3
  19. model-00011-of-00019.safetensors +0 -3
  20. model-00012-of-00019.safetensors +0 -3
  21. model-00013-of-00019.safetensors +0 -3
  22. model-00014-of-00019.safetensors +0 -3
  23. model-00015-of-00019.safetensors +0 -3
  24. model-00016-of-00019.safetensors +0 -3
  25. model-00017-of-00019.safetensors +0 -3
  26. model-00018-of-00019.safetensors +0 -3
  27. model-00019-of-00019.safetensors +0 -3
  28. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,5 +1,4 @@
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"
@@ -26,8 +25,8 @@
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
  }
 
1
  {
 
2
  "activation": "silu",
3
  "architectures": [
4
  "MixtralForCausalLM"
 
25
  "router_jitter_noise": 0.0,
26
  "sliding_window": null,
27
  "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.48.1",
30
  "use_cache": true,
31
  "vocab_size": 32128
32
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 32013,
4
  "eos_token_id": 32014,
5
- "transformers_version": "4.47.0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 32013,
4
  "eos_token_id": 32014,
5
+ "transformers_version": "4.48.1"
6
  }
model-00001-of-00019.safetensors → model-00001-of-00010.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0935408481bf83a151afb27103f27a9141d6f18aab3c7b4212d8f84a959311fe
3
- size 4989149432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f08bbe294429f0bdf3ba8244280e7db35af40bf1b9ed80250306eb9cdae50e2
3
+ size 4996025600
model-00002-of-00019.safetensors → model-00002-of-00010.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38b45737933889fe24507dcf889bae40a8e577fcfa81c2236a1a514b0dcd22d9
3
- size 4934691224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7342252c2cb66f3bf44cf95324f2e8927aff9b62371a5e38c89510f28248b1d
3
+ size 4992621528
model-00003-of-00019.safetensors → model-00003-of-00010.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7493a4be1d93e2ecc510fdd712ef9e354bba5fe6fefa13917e89ebd79d4e0be7
3
- size 4981845064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fff8c164e67c4e9c2391a1507b2e769ace4731ceaa682b3409fc32101d3ba1
3
+ size 4992621560
model-00004-of-00019.safetensors → model-00004-of-00010.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76f2b505ab19b16de888ba7ebaa6a740ab84dfb7a607015512bf143ec867de27
3
- size 4981320928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f01a310b59982fea57c8946fc69095e24287039b6e08759f6a38182b80b8559
3
+ size 4992621560
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d036f75d6bc3a8ce6a49a373344805c6047730340d423d4d1e9d3ea1b42d70f9
3
+ size 4992621704
model-00005-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f398e3dc13b51ebdb7d0d5fd45a9de041b4dad7737e61cbcfce6b4360fde357
3
- size 4981320944
 
 
 
 
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f3405d39e14890fbc9db1e6c012434cb8eb1d619beb4f25f3c5eace756d069
3
+ size 4992621984
model-00006-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a02957ce9e3af321352554d0ca5e290c41b88f132d42cfba85dd32748ee3839e
3
- size 4981320944
 
 
 
 
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c794fe64b3e116b9602c34c1b50bda90cf7404199a5f45e9955dd6e42d8cc9
3
+ size 4992113320
model-00007-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:67125ab235625185b724579ba69fcca14c2c02079a346a9a14b1cbf68d2a4c45
3
- size 4981320944
 
 
 
 
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57472f315e1465e818183463d15d1fb1fa30a02bca1f893540454c1c9fda0a5
3
+ size 4992621968
model-00008-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f511a81a213ccb7f1d2d02bf5ed1b3ce7ba7c36266cb804efde021515d8efeb
3
- size 4981320944
 
 
 
 
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae05feca8c1623d858403233a68d88a9a93adeda707055283dfba5f4fd2ea918
3
+ size 4992621992
model-00009-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a97eb7971b0187c6afef4f1ffaa9e5e87404534751ffa7554bce38d1e58238f
3
- size 4981320944
 
 
 
 
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f4560acbb5ebcbc82559a7b07b85254b6b25dd5d5953a30ec33e83852607eb1
3
+ size 1570807056
model-00010-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:02e98dbcd202e5d2403dbfe12e88d45a5ba1d22f3d06af657a369d06d641ef83
3
- size 4981321088
 
 
 
 
model-00011-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:355d5dde7a7aabf8f470eebdd2435b0027a2db5cad5406a9f5d579a4ad594b01
3
- size 4981321160
 
 
 
 
model-00012-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:74fd6b7dfa864360c9ffa379aed0b80a477a83e26648780dc69b788e354ff548
3
- size 4981321160
 
 
 
 
model-00013-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3df40b06112c43cf69191f58f387000acfac033ab8b047939e25f109f69be94
3
- size 4981321160
 
 
 
 
model-00014-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a940fd494db6a9775a76be174ed9e936c917afa3635f57a60b43f907c1b1b02
3
- size 4979780464
 
 
 
 
model-00015-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f0a0159c505d0f6cf86e5fdffa2614974e2d081984eea359d0a7eb77de9dbc5
3
- size 4981845280
 
 
 
 
model-00016-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c86a6c704cf67db7f55fcaccf4649c61942f664523e548728c2abf6612de5663
3
- size 4981321144
 
 
 
 
model-00017-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bb8aadd16f650c172e20d0ad2ec63bdbd3565523cc2d220f85bdf5f1b04f6e0
3
- size 4981321160
 
 
 
 
model-00018-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:46b851b1e35e9771235f7a68fc1f3718e0d885149a20953ab2d6f5dd71344362
3
- size 4981321160
 
 
 
 
model-00019-of-00019.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e7cf4555b5f7efea27f5dcb240460ed5684bf2620b731eb1d64a87014288b3e
3
- size 3389588112
 
 
 
 
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff