Hugging Face's logo

shisa-ai
/
global_step3500_hf

Safetensors
llama
Model card Files Community
leonardlin commited on
Commit
df1eb58
·
verified ·
1 Parent(s): 4481fd5

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 sha256:6bbe699d53e7dc8c7a7c2588ffed10e2e52ba0b380d44743fe60b967710f76e6
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:cdbfd128b5cbf568b6c808399bda8ff2f5c162d4210a477f00e451e4f3f50f73
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:f1ed5076557ae78882d9bac3c8e422d466386247ae5f8599202fda016729ded9
3
+ size 4630578112
model-00004-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d968d12998d60bda5116fd7982f01033b574b14c8ab059b28d3b05cd0ad63c
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:d4d2b4a064934938f5424f49dfe04461a4036510071d7331937f147fa867c1d0
3
+ size 3489661192
model-00006-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c71b2fd71197f59015962458e0a488687cf62c75215507cbc920fc1b49447ad
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:cadf92a84496af68ad249df17beb760a1548e3b3e360e546b3a87eaa9750b4aa
3
+ size 4630578112
model-00008-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42faba2a3ab0bd8ec0855a03a2450931ddde70b3f9edb2354283b8f54562f9dc
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:f1eed16320d38b32d526ba88788c49762c9b85fcc311dc87c57d60e12b94fd98
3
+ size 4630578112
model-00010-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b831f0da56abc8f87f8204c667c2d984d063f843467864248d517a1d7ea559f
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:eae67ba8c722cc42f96126b01bca875bd3602ee8be2550f60ffc47ef2820b642
3
+ size 3489661192
model-00012-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a07cbefde66877772b6b7b267af294bcf9cd893977ff8592b6b4a7418e69e9
3
+ size 4630578112
model-00013-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379da1ee9d98b9f2771651ccecdfb3cd16a39951bfda9ba8aa7b67d3f5fa8ff8
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:b3327fd8796303754dbc3af3e9343da4807e186d73a9350ebde056ce65623035
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:ae1f693ce5c71d7941fe37735515b756fbe3240238335726aced4ecc88d29402
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:b325adfb3d180cf9258ad3ca017f117492447965bfba226b46a9712559ca389a
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:da9c0203882043995c95e00fb1b201d268cc8f2081158a94202fabc1107cf908
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:c54c51ff5334aaf57da271e742ce3781223f73caf61ab893a40aeda93e9769bb
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:aee20d1abe2c110cf343b30d083baf26a42fe44017fe8bec8e31486680b37947
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:ae3bd0975d821aa785bef74fe02e55eb1873f8abcf18c8ac8aaf1966f9845cbb
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:e460fccec8ed1451ecc7fb04f82bf78e00e3529323e5d6c9c26b5e2032a402f6
3
+ size 4630578120
model-00022-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4880dce8326e9a0b680ec236a03cf0586f35d0a284671ea28f9b4517270647c4
3
+ size 4630578120
model-00023-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02847268b2cea61276e69c894f6ec39b2c211256cf39efef69c34397aea7f96f
3
+ size 3489661192
model-00024-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d9bc3ce6e8da8f5a429cff7d997935fcc1830c1879d12240ca412e9ccac937
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:a29fb71cf49d0101255465e5725acbb18f057812152a844ae109d4795de305b5
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:baa2af229d3e3926e8a66a03c1ecda0c77608497c297549846d66bfa6d3db892
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:d4df2c3d15e26bf2ec7db964ef1a3f5818f037e12f082f8757d6dc4cbd5ac22d
3
+ size 4630578120
model-00028-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f1c286e255de6676076eeefc9c34999f91d4613a065310013290baa89a451a
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:b75602c2249bd0e5fcbe503b6c06575581cdb834f61a6e6d09abbcb41f4bfc9b
3
+ size 3489661192
model-00030-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f76b766f233e0c7ad970eb1b6cc806ad4bd58a613e8edf8d7ede2518daeed0
3
+ size 4630578120
model-00031-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c06fa5aef3a2f00c14183e63994b0d381bbe9ac15587fe617e22eb2555b4fd9
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:cc1b6fcf7e91e502b42887781686cdee1699f035ccc1c96f2758b4e27a63ecf0
3
+ size 3489661192
model-00033-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2369fd4de44bb5ce3ad8097e8f2181a591f71818ae0ee2b36f408bcad4a8b69d
3
+ size 4630578120
model-00034-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7f8f670f7d42432c7a1802a6ce6f5b2820473ea2a709790e2ef8f35601a0c3
3
+ size 4630578120
model-00035-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058f119bb1481350de2aa9d063f764cc7ce31c6026b1732da9138e63a716c4d5
3
+ size 3489661192
model-00036-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c05ce0f147c6021dd6ddd335eb32ba9e0fe03121af2295bfa6e27462bc2d4c
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:ef6c9922a6580822e299bc32e1cb93b4b6cbb82c611c2486c49897ed0511a269
3
+ size 4630578120
model-00038-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511af5c1214515569e11e0387784cd0f19ec7e7bf5efb7a84f67cb46719c914c
3
+ size 3489661192
model-00039-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f33dc9e2564eb6afb94737c673b1fd5261e7becfaf1615fbf6bdbe59d23251
3
+ size 4630578120
model-00040-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7939e185f3c37bbaa8be927dddf8d777d37ac0f449b8a50af0d6d853d8e341a3
3
+ size 4630578120
model-00041-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fac0bfb3cd1a4a05d106ca478d20a64d60bf782e46ad88b878a1ba032c23b9b
3
+ size 3489661192
model-00042-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f09f9c22cf7d8f8f070893046ac13ceb086be9d38ac22084ae7de2fbb3b6084
3
+ size 4630578120
model-00043-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ffdc760e0ba8e06d793ad41640b75f569568df4f31b3124aa08915c8cee866a
3
+ size 4630578120
model-00044-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:471840f5efb5d753419f1f11d66d3521e7fd2f79f8a45ba4847b3a54b9913475
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:e3873c2ef5bee67c093fa227253c1259d0220757d4dfe3a1a1a9637bac3e6a9d
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:e1391988f9fc8218b00447a0ae87b52dae6b40618c80132a04737585e01d7cb0
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:e720e30d1bb1b3e82c10aaec8836aefddf01a09842e6bd5955faf19774a5e021
3
+ size 3489661192