Hugging Face's logo

shisa-ai
/
global_step4500_hf

Safetensors
llama
Model card Files Community
leonardlin commited on
Commit
d27d44c
·
verified ·
1 Parent(s): 44e691a

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 sha256:5976c4d8c2b0e44704389329d2ba6801b460a495c8297eec4b5c620800589cdc
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:bab468bd4484453617cc6400a172c562bda99e354cf3defc9588a145849d4fe0
3
+ size 4026532224
model-00003-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d016bff40214c045037c80c9bebbd0b4cfdc66011571269630f708d9cdb1583
3
+ size 4630578112
model-00004-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66682bcc6789093886967b1a4346b67ce8bcda225ae2bb3def410dbf3db83d4c
3
+ size 4630578112
model-00005-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450a1644adc317eb4396fed8665a82ce060304348931eeef8dc95cb6741a8b55
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:a0ed433574d2c33ac603a533e127f9c769082c523b08ae41556dc667500b1a7e
3
+ size 4630578112
model-00007-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc5cf433f6f14cd7b024502e8a4bfe7569c7132c8f55938665f0bde7a1a289b
3
+ size 4630578112
model-00008-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e6f22bfe4751d031b2bf663a6e5b7e629491fd19cc4d431cc508a28a8758df
3
+ size 3489661192
model-00009-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afef354a7168bc14ed522db72aef49f5ee5ec32b0aa90c9319fb77087792cfc
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:a4349b47c162bebe88dfa12a665f5c035366922fdc890b99e85c7095a6cf5d1f
3
+ size 4630578112
model-00011-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6816806ec02d5c572dfb6a95e83316355f209fe5f5f679136dccaf94ef3c31f0
3
+ size 3489661192
model-00012-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2a8d4c49ce23d4f2a9cac0aaa41eb5bae1f72eb637609e09b4e88635321822
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:e229db3e4b50f1161b9090416b2d3ac34f7005c12ec315ae04a0bbfb75bf60d3
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:a95ad2e795fb2240bd4d93ef03208609cd29096d3e08df381fc90bb7b1d27877
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:b8edc5885b6f828730e9c8f0a3f073b57e9b430f6b7ff431496150c709a6e2fe
3
+ size 4630578112
model-00016-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d278f23044006ea6d5c683943da606de6c4eab960f7726c0bc45dfe50544862
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:a2605b0ff7299e8189524df6494e7691ae9b28427728f248e7ecbf23032f0d75
3
+ size 3489661192
model-00018-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053ab688663b5ef16e656b60e5ba21f80ac478376e01aae2f8288715859c6b36
3
+ size 4630578120
model-00019-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecb1a8e281f54ea70e673d0d4c4d2600eef81f3739a016b7de954864a15a81c
3
+ size 4630578120
model-00020-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aebc61e64bd8cea3f30da3549dc55b0be9a83792be9903f6164d3163831e033
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:d5c21c2317a528a2ecd82b3149b427d38aa6ebf08df6b7ff1c5089aed8a99d27
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:b7fb06add318ec562da10d521d9325b43f3b1813f1d40085d016d7a7f2aafc73
3
+ size 4630578120
model-00023-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005943a73eb7d2727b5ae74431803535fd879c97ca947a9e2aa21e674ee2a798
3
+ size 3489661192
model-00024-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8520666b55731898072f14d328557b9cbf97e68ba6ac781adb9833c4e9fe8a92
3
+ size 4630578120
model-00025-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3219567323c0142d667a23e45e8145990170437f82dace91a1dead6a859e8526
3
+ size 4630578120
model-00026-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa4901233815986bd7b0bc5fb46e9021558fc43d528006a2bc8175715e13ebd
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:b8d65c2942c695cac068a2d398878e0a7d667e396dac456ae9e0dda38c20e71e
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:b8333b652989abfedbbc96f4d39e345518ccb9275e115424aef5a4c745068655
3
+ size 4630578120
model-00029-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5060f549fd5d1d31b51f0582dcfb2c47d64cc4562ffadf5c8f33b19488e271e5
3
+ size 3489661192
model-00030-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0611a58bb43dc652d8337359bc3c677bca748095d44e9531ca2efd5c7cdf28e9
3
+ size 4630578120
model-00031-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af06d038fcc7a4c834ab2acd9bc2af77831672e8ab42a85a04ce6ee7c577b24
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:c66f8575d28374cf32b8dd68e3cc98acd0c65c74dabd55a0a308a5d5fbe8d41f
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:a7cde3d5d09f0cda2aa4ee5abef362a56fa6ffaaa8ef4914ed5ed278e95b5d70
3
+ size 4630578120
model-00034-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05078c9c1d6169ab856e91e535213533c9f42810a34c70536b56271987ff425f
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:ce86ad4b0d3daeb8641ae02a17c3a357a972dba48c79206d1664ef8f80cd9b6c
3
+ size 3489661192
model-00036-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797deca143990ba08c840f82443006073a689e6a6994b12c6b3b0bc4ccbd28d4
3
+ size 4630578120
model-00037-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6990d775548315da514f164964d9ef095b5157a8db1c4e80f255bd59495841a8
3
+ size 4630578120
model-00038-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb11d303b7e0c44dec6db99a266a1d34aceee6f08c1c3b074114fc28592c370
3
+ size 3489661192
model-00039-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a83950f16a490d27f7150797756a3a2bf7e6fa1da48eb2cb2643ae41a127ac
3
+ size 4630578120
model-00040-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015a7b0f09ff98aba4e8918c282352cbe7d5d1516ff2ebb65afb1e1eb6495628
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:a39d5739401094e1bd859272a0606ff9dda72328d9edb49642de08622506c3a0
3
+ size 3489661192
model-00042-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8505f9cdddb3c1d34e9dd1ebf94f8de26016b72942ab1774e4e44bb53293c543
3
+ size 4630578120
model-00043-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6529f33fdfa8a461a92c8ac44ad7e3c7518ca7fd8a42e8f873500f744c17a650
3
+ size 4630578120
model-00044-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735e8aceb154f0ab33587c36cd2258633d4b098d736a357085ef8a80056d3322
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:bc44eca5f6bad8529b9e0b5f17d1dbc5d379bebc2a3ac66b015dc39e4943a323
3
+ size 4630578120
model-00046-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869c052749e3ade33dfd55c014b9a19a243ec89a224bfebb9fed56f46cf233f9
3
+ size 4630578120
model-00047-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85063924333313d7d19abf295d457c9b21cdc5524e6b04aa9b9435c3d20ae0c0
3
+ size 3489661192