Hugging Face's logo

shisa-ai
/
shisa-v2-llama3.1-405b

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files Community
leonardlin commited on
Commit
71b83a7
·
verified ·
1 Parent(s): 21c06b5

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. config.json +40 -0
  3. generation_config.json +12 -0
  4. model-00001-of-00191.safetensors +3 -0
  5. model-00002-of-00191.safetensors +3 -0
  6. model-00003-of-00191.safetensors +3 -0
  7. model-00004-of-00191.safetensors +3 -0
  8. model-00005-of-00191.safetensors +3 -0
  9. model-00006-of-00191.safetensors +3 -0
  10. model-00007-of-00191.safetensors +3 -0
  11. model-00008-of-00191.safetensors +3 -0
  12. model-00009-of-00191.safetensors +3 -0
  13. model-00010-of-00191.safetensors +3 -0
  14. model-00011-of-00191.safetensors +3 -0
  15. model-00012-of-00191.safetensors +3 -0
  16. model-00013-of-00191.safetensors +3 -0
  17. model-00014-of-00191.safetensors +3 -0
  18. model-00015-of-00191.safetensors +3 -0
  19. model-00016-of-00191.safetensors +3 -0
  20. model-00017-of-00191.safetensors +3 -0
  21. model-00018-of-00191.safetensors +3 -0
  22. model-00019-of-00191.safetensors +3 -0
  23. model-00020-of-00191.safetensors +3 -0
  24. model-00021-of-00191.safetensors +3 -0
  25. model-00022-of-00191.safetensors +3 -0
  26. model-00023-of-00191.safetensors +3 -0
  27. model-00024-of-00191.safetensors +3 -0
  28. model-00025-of-00191.safetensors +3 -0
  29. model-00026-of-00191.safetensors +3 -0
  30. model-00027-of-00191.safetensors +3 -0
  31. model-00028-of-00191.safetensors +3 -0
  32. model-00029-of-00191.safetensors +3 -0
  33. model-00030-of-00191.safetensors +3 -0
  34. model-00031-of-00191.safetensors +3 -0
  35. model-00032-of-00191.safetensors +3 -0
  36. model-00033-of-00191.safetensors +3 -0
  37. model-00034-of-00191.safetensors +3 -0
  38. model-00035-of-00191.safetensors +3 -0
  39. model-00036-of-00191.safetensors +3 -0
  40. model-00037-of-00191.safetensors +3 -0
  41. model-00038-of-00191.safetensors +3 -0
  42. model-00039-of-00191.safetensors +3 -0
  43. model-00040-of-00191.safetensors +3 -0
  44. model-00041-of-00191.safetensors +3 -0
  45. model-00042-of-00191.safetensors +3 -0
  46. model-00043-of-00191.safetensors +3 -0
  47. model-00044-of-00191.safetensors +3 -0
  48. model-00045-of-00191.safetensors +3 -0
  49. model-00046-of-00191.safetensors +3 -0
  50. model-00047-of-00191.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 16384,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 53248,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 128,
22
+ "num_hidden_layers": 126,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 128009,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.50.0",
38
+ "use_cache": false,
39
+ "vocab_size": 128256
40
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.50.0"
12
+ }
model-00001-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7dd5073d3af0efb07b79ef26b0dbd17a1ad7f2c7da8bcd231d6e78343dad3c
3
+ size 4806672880
model-00002-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a98b73b36521dd74efec374621359cca97c082f7905191c0927fa8b27fa97a
3
+ size 4026532224
model-00003-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e53baff81829ee59e2d411db7a1afdefedeffec0bce5566db4160910babeb7
3
+ size 4630578112
model-00004-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d767357cc3f09f082f370a6bc3e4378f9d49ede2d7f5e93c5d8915ed7b1c1773
3
+ size 4630578112
model-00005-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7961f57632c4853f6bb35823ec6b30fcb81882bfa79041832d9e20e0bc845384
3
+ size 3489661192
model-00006-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7974c2839603e3981ee2fed2e48e58d45ed94fd84c7a3f52927524aa509f99
3
+ size 4630578112
model-00007-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa9062d7e86a14ab217b5c30e0361fe4bfedceb0de1f98b08121a14e0935beb
3
+ size 4630578112
model-00008-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a944660f67572d121bfe6ccc6fa248560150485ef9828ab52774943a531e1498
3
+ size 3489661192
model-00009-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d426b46b0f3b709731009d5b986dfa3be9cf3c77291c148d229f5645a59c4df1
3
+ size 4630578112
model-00010-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e31b11a666ad306db70e5ec7eb77cfc0f283788d028acd05b43059e1e9ad552
3
+ size 4630578112
model-00011-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24606cfd1225a68c4e6a5e9a22464bc48c8f3ca69c787010d98271a1f16e053b
3
+ size 3489661192
model-00012-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:761bc11645eb24402db3962a100c221888a7f7ba4f7a22c14b1754f22f0a56be
3
+ size 4630578112
model-00013-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf2f3d978203f1e8c6ab50f9ea1f9cb8417003bf8ffddfc55b62e720092bb1da
3
+ size 4630578112
model-00014-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f25fb7d43b191552537c1e306a211de3f1951a2947a4d3830d532fb648c49db
3
+ size 3489661192
model-00015-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c6bd4ab26fa24223f3b50096a5276763fea0abddb4d52da35e91e6ee4cd2079
3
+ size 4630578112
model-00016-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b96a999d5676f35ea0e0c34db10898bdbb9434649400c2932644f47ef4642e50
3
+ size 4630578120
model-00017-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af65fa49c9f0ebab8dddf51bc089ee92eccf4f4ead77cdd2aa1f8c79d41d49e1
3
+ size 3489661192
model-00018-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4776048d3d7d06de21f65b8749b24b2438f969846cd73ff7765dff18274228ad
3
+ size 4630578120
model-00019-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228c5868ee7727f4f921d6315cbb7d94cab59aa63b2158025796636e2815e640
3
+ size 4630578120
model-00020-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b802fdb851cf1d0152cbf81163c919fc850099fa54c8b4257d66632dae0e087
3
+ size 3489661192
model-00021-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:142fa2bb6018c2185a756cc2e21d994f19023f06e085f5e3fbed27c642f5c926
3
+ size 4630578120
model-00022-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11176eb98585c0aeec14a20dae5207cd0462dd2cbc4de83b08bced9c4ed90655
3
+ size 4630578120
model-00023-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04cd4a9abe3b8d4c5d8b5717be57c6e51ef7e47f57de18aef9d34fe8757850a1
3
+ size 3489661192
model-00024-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e4fe8c96d9e4d55ce2faa4832c5a7a6f6e73cc1a58092ca106bff6d8adf9b0
3
+ size 4630578120
model-00025-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c25d3b8f0fe6472ff334e16dcf1d63fc62d843b715f2b43a9ae30d48cb5524
3
+ size 4630578120
model-00026-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1e3f6774c6fe05ebfc0847d9678a320a00964d4d58acc58eb5e762a9442efc
3
+ size 3489661192
model-00027-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbdb8a4ae19a9d9e56c8df40d00807e0010247b69fd1f9a6afaa44f07560d7b4
3
+ size 4630578120
model-00028-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498e803d99ef3bebe941904e82bc0a1e2f340dc1e6e956945a5a9857acfb024b
3
+ size 4630578120
model-00029-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b677a6c711d92c316e565bc6497f06f62f03f6b1ae8c1f489fa4a892ba2acc7
3
+ size 3489661192
model-00030-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d5bf7794fd862b1bc16b034833aae3e4ef334c47ab209f325e966e5607df16
3
+ size 4630578120
model-00031-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdebaef9f2015623e80e62aaa34a743cd555e002f7bcf3d03276e29e702fd8ae
3
+ size 4630578120
model-00032-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f153518dab9746e725c6e38e376041793a50196682fb155640911f9c4b80137f
3
+ size 3489661192
model-00033-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9baebf819b0e73ad5e9078f04f4fe850f7d8f85f323627e4d8a60811cbbb851
3
+ size 4630578120
model-00034-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bddc37cf0610db68e767c449d5e0cf2f8a8df2c3a08844bc6d781d44ecb9ba1
3
+ size 4630578120
model-00035-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03495ede4889cb41e323284b21270be893999f5b2d89f9ea52a0e3350f43262
3
+ size 3489661192
model-00036-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c5efd01e20a4d6e3dc6cc61ed1f87d4c31f5f0fa0f45f884cea8ab45bbed48
3
+ size 4630578120
model-00037-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece2055543310b884ddfcdf479dba7ba498e9c03cc88899aa52568d561f92e82
3
+ size 4630578120
model-00038-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa14c3b7dd4eee7b5d189ecf00621076be08c2d2e2e14c4f22f004d4699b5665
3
+ size 3489661192
model-00039-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce235c2ce71ea1f477e06f105c6f152de894344ee64129bdfd1ee74a62a4e6a
3
+ size 4630578120
model-00040-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e79a085ed3bd3bbe7c97ca5374e08fa2ab22a83a5a2bba80f7b1cd9f5f15b02
3
+ size 4630578120
model-00041-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0df30d2f260adc17e3d2dd29bddfde7964bc836b0a1eeef06d671c5702beb4
3
+ size 3489661192
model-00042-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c771385dcb1f9544968ae40f6d1f890abb66274ccd60d57eb43f470f1454b24
3
+ size 4630578120
model-00043-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d694260d0b201c6fd2e9d1d2f917876cb25d7880483e5e0b1c96361f1a52b06c
3
+ size 4630578120
model-00044-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47c21a66fd9d3d33f93f2887df6a2344dfd8e3a30f1e14dcbf6c2098ecc5b74
3
+ size 3489661192
model-00045-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdfd7b5d1800c21e5467028bca4893744f74b0d4d966e9cfa06d1b0fe132c59
3
+ size 4630578120
model-00046-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1f1914b91729797c7efcb8c680277421a632bcc90e457b629058c2b1d2e5f7
3
+ size 4630578120
model-00047-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc241918e27992d8d92c5c129cb2de3c04fe7425db427e80e327ab33ad561bd
3
+ size 3489661192