Hack337 commited on
Commit
b90215a
·
verified ·
1 Parent(s): cfe26a5

Upload 49 files

Browse files
Files changed (49) hide show
  1. config.json +28 -0
  2. generation_config.json +14 -0
  3. model-00001-of-00044.safetensors +3 -0
  4. model-00002-of-00044.safetensors +3 -0
  5. model-00003-of-00044.safetensors +3 -0
  6. model-00004-of-00044.safetensors +3 -0
  7. model-00005-of-00044.safetensors +3 -0
  8. model-00006-of-00044.safetensors +3 -0
  9. model-00007-of-00044.safetensors +3 -0
  10. model-00008-of-00044.safetensors +3 -0
  11. model-00009-of-00044.safetensors +3 -0
  12. model-00010-of-00044.safetensors +3 -0
  13. model-00011-of-00044.safetensors +3 -0
  14. model-00012-of-00044.safetensors +3 -0
  15. model-00013-of-00044.safetensors +3 -0
  16. model-00014-of-00044.safetensors +3 -0
  17. model-00015-of-00044.safetensors +3 -0
  18. model-00016-of-00044.safetensors +3 -0
  19. model-00017-of-00044.safetensors +3 -0
  20. model-00018-of-00044.safetensors +3 -0
  21. model-00019-of-00044.safetensors +3 -0
  22. model-00020-of-00044.safetensors +3 -0
  23. model-00021-of-00044.safetensors +3 -0
  24. model-00022-of-00044.safetensors +3 -0
  25. model-00023-of-00044.safetensors +3 -0
  26. model-00024-of-00044.safetensors +3 -0
  27. model-00025-of-00044.safetensors +3 -0
  28. model-00026-of-00044.safetensors +3 -0
  29. model-00027-of-00044.safetensors +3 -0
  30. model-00028-of-00044.safetensors +3 -0
  31. model-00029-of-00044.safetensors +3 -0
  32. model-00030-of-00044.safetensors +3 -0
  33. model-00031-of-00044.safetensors +3 -0
  34. model-00032-of-00044.safetensors +3 -0
  35. model-00033-of-00044.safetensors +3 -0
  36. model-00034-of-00044.safetensors +3 -0
  37. model-00035-of-00044.safetensors +3 -0
  38. model-00036-of-00044.safetensors +3 -0
  39. model-00037-of-00044.safetensors +3 -0
  40. model-00038-of-00044.safetensors +3 -0
  41. model-00039-of-00044.safetensors +3 -0
  42. model-00040-of-00044.safetensors +3 -0
  43. model-00041-of-00044.safetensors +3 -0
  44. model-00042-of-00044.safetensors +3 -0
  45. model-00043-of-00044.safetensors +3 -0
  46. model-00044-of-00044.safetensors +3 -0
  47. model.safetensors.index.json +346 -0
  48. tokenizer.json +0 -0
  49. tokenizer_config.json +208 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.43.3",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.43.3"
14
+ }
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c182b21dad00dbddb591b097459426b822cc13e2572a4c721bbd7ac863f0dcda
3
+ size 1089994888
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e87fbb6c86f0b75c1b2ffae1a941a51007454554810b565a7ee1d038fca45e9
3
+ size 330311688
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34e7a37cc41828bb6068a43eb8764312f14d8c9303a669283d44fd677d25f55a
3
+ size 330326240
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5173c29744cb9e45c056e5dcf790738f05f5154b30b1dd37441b7e5d72f273
3
+ size 330326240
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149425f7007e49db3e2a57060fe87a91813edd4a94a0c4a4caf424e6fb6b9f96
3
+ size 271581440
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:941a04823a4b8a7152af709373f2853dba64226f728c65d776c60db6f2d08cbc
3
+ size 330326240
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0557143229ad65389dc61783612800e3d1729456d5bfa0dbd2f3b6f4fe799f42
3
+ size 330326240
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425d1375753d3ae7122418055be2842c01e02cf45ad6733769d76585b15348df
3
+ size 271581440
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7fbb6184644dc207191c9ea3ad4c0a997c060184ff8b5cd7daf141f601c9859
3
+ size 330326240
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f131835ec963a9f699f75f95e521b6463de68b1b7b1094f31477172c4b9c67d
3
+ size 330326240
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039f191d3bb7954866e4e264419717901205f7e14526c3e983a987083f121539
3
+ size 271581440
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db889fba6293d77fc41aceb45b0e0103cb6fc1288ea1e6ef589635d33a9df5ee
3
+ size 330326240
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdc4f159e7238a21f3f4e3f2ca3f0efb98eb454c6fe41c7bd002fcca774da29
3
+ size 330326240
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5434a9b16ecc025201da6c39ac8d7ced9335254f08400f7bb52406bbd7cf7bbc
3
+ size 271581440
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66de117a6120ad8b8d81883bd5b96b188b15ad6629311774cfb39344626858d1
3
+ size 330326240
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5158998750bc10db8122586264a7ca74ee096f666e57afd51e477978ef1ad9f
3
+ size 330326232
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a2054eb9b058c2f9e875d09b0db6ee55a6493b52b5ec97acc97a71f3739dbd
3
+ size 271581440
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997f98d737be05819a31763cf76a6b7e203c7dc3bb1d65da2654ec3d98317638
3
+ size 330326248
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d38397b00e7629115df5e2794ca1735d33a4c12476e69ca8528c5429fea7f8ec
3
+ size 330326248
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759b8bb9a068108936b1691e9fc66da8a63e90dece021f306c612743bd7b7929
3
+ size 271581440
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a7850c1dd3332f997d2cb7d6852991e30634ca56d3428ddae482118cd57af7
3
+ size 330326248
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828ab9de8ea7ec7e9cb65f225afd64b2ed3414302d80f52ba02153ca516659ca
3
+ size 330326248
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096a5b15cab41e41d8941bd6715bc0f8d560037ac53d855df5891b004502808b
3
+ size 271581440
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22585906c1cc74b37f8686c9be63b9a3e83d2aa93a637233b6bc0b4d2b375b2e
3
+ size 330326248
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3faa320688596c99ebe50938d132bb2db8c3d6920bafd973a9a605dd609e88e6
3
+ size 330326248
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef03144701efc2bf38ba29081a696cf48371c88cda636e64e81d7898b9d0e2c
3
+ size 271581440
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d7884ba223359d496218263480ac803cfd81f9f51072cb641fa9fedf5e9315
3
+ size 330326248
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40214a2fbe847051112f71f605939a519241f0f88201ef9cf0d58838a4beef84
3
+ size 330326248
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f538ce6d716a69e1603ef0b362811dcb9fa2831bd28fbdeafa6a9677cfc7711
3
+ size 271581440
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a31e698b5b55c80cd2d70d252a6b0a74371bbd06da3f6373ad233855dcea99c
3
+ size 330326248
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b7300758b24d0f96fd0640cb1b038945752866bb336d1c3eea8cf83021c81e
3
+ size 330326248
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31391694d6cf7c3e755fe113a0353159a00d25d1292a47e0f96ff2f0f59b86c1
3
+ size 271581440
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9a6ffea3a9ab3296663a644e5d3bd6944bbb7db4060ab31430d4574c47199b
3
+ size 330326248
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e36ce7847afa500a3ff0f5f05c9d6b63bf4e71dd3e8e35f807351d51a11a8ff
3
+ size 330326248
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d568b2d169bbdc1c49ede8f4e2e6e81dc3b32140f4c8e4bf2c37888b236c89d6
3
+ size 271581440
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a11b3a27cfd8d1269501b65fd71fd93e72c9f09014e7eaf9908ad0695145c22
3
+ size 330326248
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d28069abf2d225bd64486554fe8317a0409778a76d2e7892c1745b656ac3af4
3
+ size 330326248
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338f33d70f92e272cfe9549bc6ad158568713f59e9ef135eff3d625ba1da4822
3
+ size 271581440
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f62d0492ad27bfaa6338911b0c77f65dc452cc2c971929a28892834f88ed00
3
+ size 330326248
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9015fdc09cc62370ea4dbe45652a30ba2b2155c059446da6f1d9367cc5a14ea0
3
+ size 330326248
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c02cfbb4b389b078a0aedaea4e5fc82a95e44ca8f51751f0c76e19e46e8da0
3
+ size 271581440
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca83138c87931587fd1827dd01f01715e48f1654a58eda8214dc4424d41cb17e
3
+ size 330326248
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053d06aa9a6579967b3653c789151a7edf361899e7804c10a756b53286f602e8
3
+ size 1089994880
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62915ab4c72f4bcafae1535f15942211dfa59c32ea47c93962d16f08164ab5ff
3
+ size 271603256
model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00043-of-00044.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00044.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00003-of-00044.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00003-of-00044.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00044.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00044.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00044.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00044.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00004-of-00044.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00004-of-00044.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00044.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00004-of-00044.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00044.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00044.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00044.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00044.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00044.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00044.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00044.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00044.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00018-of-00044.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00018-of-00044.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00017-of-00044.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00017-of-00044.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00044.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00016-of-00044.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00016-of-00044.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00016-of-00044.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00016-of-00044.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00016-of-00044.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00016-of-00044.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00016-of-00044.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00019-of-00044.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00019-of-00044.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00018-of-00044.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00019-of-00044.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00019-of-00044.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00018-of-00044.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00018-of-00044.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00018-of-00044.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00018-of-00044.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00044.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00018-of-00044.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00018-of-00044.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00021-of-00044.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00021-of-00044.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00020-of-00044.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00020-of-00044.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00021-of-00044.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00019-of-00044.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00044.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00044.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00019-of-00044.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00019-of-00044.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00019-of-00044.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00044.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00022-of-00044.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00022-of-00044.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00021-of-00044.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00022-of-00044.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00022-of-00044.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00021-of-00044.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00021-of-00044.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00021-of-00044.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00021-of-00044.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00021-of-00044.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00021-of-00044.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00021-of-00044.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00024-of-00044.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00024-of-00044.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00023-of-00044.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00023-of-00044.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00024-of-00044.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00022-of-00044.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00022-of-00044.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00022-of-00044.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00022-of-00044.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00022-of-00044.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00022-of-00044.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00022-of-00044.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00025-of-00044.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00025-of-00044.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00024-of-00044.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00025-of-00044.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00025-of-00044.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00024-of-00044.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00024-of-00044.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00024-of-00044.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00024-of-00044.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00024-of-00044.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00024-of-00044.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00024-of-00044.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00027-of-00044.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00027-of-00044.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00026-of-00044.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00026-of-00044.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00027-of-00044.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00025-of-00044.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00025-of-00044.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00025-of-00044.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00025-of-00044.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00025-of-00044.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00025-of-00044.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00025-of-00044.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00028-of-00044.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00028-of-00044.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00027-of-00044.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00028-of-00044.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00028-of-00044.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00027-of-00044.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00027-of-00044.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00027-of-00044.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00027-of-00044.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00027-of-00044.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00027-of-00044.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00027-of-00044.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00030-of-00044.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00030-of-00044.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00029-of-00044.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00029-of-00044.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00030-of-00044.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00028-of-00044.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00028-of-00044.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00028-of-00044.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00028-of-00044.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00028-of-00044.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00028-of-00044.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00028-of-00044.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00031-of-00044.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00031-of-00044.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00030-of-00044.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00031-of-00044.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00031-of-00044.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00030-of-00044.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00030-of-00044.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00030-of-00044.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00030-of-00044.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00030-of-00044.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00030-of-00044.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00030-of-00044.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00006-of-00044.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00006-of-00044.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00044.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00005-of-00044.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00044.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00004-of-00044.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00044.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00044.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00004-of-00044.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00044.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00044.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00044.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00033-of-00044.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00033-of-00044.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00032-of-00044.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00032-of-00044.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00033-of-00044.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00031-of-00044.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00031-of-00044.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00031-of-00044.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00031-of-00044.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00031-of-00044.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00031-of-00044.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00031-of-00044.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00034-of-00044.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00034-of-00044.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00033-of-00044.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00034-of-00044.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00034-of-00044.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00033-of-00044.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00033-of-00044.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00033-of-00044.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00033-of-00044.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00033-of-00044.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00033-of-00044.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00033-of-00044.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00036-of-00044.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00036-of-00044.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00035-of-00044.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00035-of-00044.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00036-of-00044.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00034-of-00044.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00034-of-00044.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00034-of-00044.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00034-of-00044.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00034-of-00044.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00034-of-00044.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00034-of-00044.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00037-of-00044.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00037-of-00044.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00036-of-00044.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00037-of-00044.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00037-of-00044.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00036-of-00044.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00036-of-00044.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00036-of-00044.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00036-of-00044.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00036-of-00044.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00036-of-00044.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00036-of-00044.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00039-of-00044.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00039-of-00044.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00038-of-00044.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00038-of-00044.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00039-of-00044.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00037-of-00044.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00037-of-00044.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00037-of-00044.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00037-of-00044.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00037-of-00044.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00037-of-00044.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00037-of-00044.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00040-of-00044.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00040-of-00044.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00039-of-00044.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00040-of-00044.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00040-of-00044.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00039-of-00044.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00039-of-00044.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00039-of-00044.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00039-of-00044.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00039-of-00044.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00039-of-00044.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00039-of-00044.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00042-of-00044.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00042-of-00044.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00041-of-00044.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00041-of-00044.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00042-of-00044.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00040-of-00044.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00040-of-00044.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00040-of-00044.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00040-of-00044.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00040-of-00044.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00040-of-00044.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00040-of-00044.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00044-of-00044.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00044-of-00044.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00042-of-00044.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00044-of-00044.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00044-of-00044.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00042-of-00044.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00042-of-00044.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00042-of-00044.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00042-of-00044.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00042-of-00044.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00042-of-00044.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00042-of-00044.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00007-of-00044.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00007-of-00044.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00044.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00007-of-00044.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00044.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00006-of-00044.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00044.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00044.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00006-of-00044.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00044.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00006-of-00044.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00044.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00009-of-00044.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00009-of-00044.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00044.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00008-of-00044.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00044.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00007-of-00044.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00044.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00044.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00007-of-00044.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00044.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00007-of-00044.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00044.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00010-of-00044.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00010-of-00044.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00044.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00010-of-00044.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00044.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00009-of-00044.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00044.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00044.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00009-of-00044.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00044.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00009-of-00044.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00044.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00012-of-00044.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00012-of-00044.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00011-of-00044.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00011-of-00044.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00044.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00010-of-00044.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00044.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00044.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00010-of-00044.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00044.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00010-of-00044.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00044.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00013-of-00044.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00013-of-00044.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00012-of-00044.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00013-of-00044.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00044.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00012-of-00044.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00044.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00044.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00012-of-00044.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00044.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00012-of-00044.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00044.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00015-of-00044.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00015-of-00044.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00044.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00014-of-00044.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00015-of-00044.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00013-of-00044.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00044.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00044.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00013-of-00044.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00044.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00013-of-00044.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00044.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00016-of-00044.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00016-of-00044.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00044.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00016-of-00044.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00044.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00015-of-00044.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00044.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00044.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00015-of-00044.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00044.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00015-of-00044.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00044.safetensors",
344
+ "model.norm.weight": "model-00044-of-00044.safetensors"
345
+ }
346
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }