littlebird13 commited on
Commit
49cccf8
·
verified ·
1 Parent(s): 0965c4f

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 +46 -0
  3. merges.txt +0 -0
  4. model-00001-of-00048.safetensors +3 -0
  5. model-00002-of-00048.safetensors +3 -0
  6. model-00003-of-00048.safetensors +3 -0
  7. model-00004-of-00048.safetensors +3 -0
  8. model-00005-of-00048.safetensors +3 -0
  9. model-00006-of-00048.safetensors +3 -0
  10. model-00007-of-00048.safetensors +3 -0
  11. model-00008-of-00048.safetensors +3 -0
  12. model-00009-of-00048.safetensors +3 -0
  13. model-00010-of-00048.safetensors +3 -0
  14. model-00011-of-00048.safetensors +3 -0
  15. model-00012-of-00048.safetensors +3 -0
  16. model-00013-of-00048.safetensors +3 -0
  17. model-00014-of-00048.safetensors +3 -0
  18. model-00015-of-00048.safetensors +3 -0
  19. model-00016-of-00048.safetensors +3 -0
  20. model-00017-of-00048.safetensors +3 -0
  21. model-00018-of-00048.safetensors +3 -0
  22. model-00019-of-00048.safetensors +3 -0
  23. model-00020-of-00048.safetensors +3 -0
  24. model-00021-of-00048.safetensors +3 -0
  25. model-00022-of-00048.safetensors +3 -0
  26. model-00023-of-00048.safetensors +3 -0
  27. model-00024-of-00048.safetensors +3 -0
  28. model-00025-of-00048.safetensors +3 -0
  29. model-00026-of-00048.safetensors +3 -0
  30. model-00027-of-00048.safetensors +3 -0
  31. model-00028-of-00048.safetensors +3 -0
  32. model-00029-of-00048.safetensors +3 -0
  33. model-00030-of-00048.safetensors +3 -0
  34. model-00031-of-00048.safetensors +3 -0
  35. model-00032-of-00048.safetensors +3 -0
  36. model-00033-of-00048.safetensors +3 -0
  37. model-00034-of-00048.safetensors +3 -0
  38. model-00035-of-00048.safetensors +3 -0
  39. model-00036-of-00048.safetensors +3 -0
  40. model-00037-of-00048.safetensors +3 -0
  41. model-00038-of-00048.safetensors +3 -0
  42. model-00039-of-00048.safetensors +3 -0
  43. model-00040-of-00048.safetensors +3 -0
  44. model-00041-of-00048.safetensors +3 -0
  45. model-00042-of-00048.safetensors +3 -0
  46. model-00043-of-00048.safetensors +3 -0
  47. model-00044-of-00048.safetensors +3 -0
  48. model-00045-of-00048.safetensors +3 -0
  49. model-00046-of-00048.safetensors +3 -0
  50. model-00047-of-00048.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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12288,
15
+ "max_position_embeddings": 40960,
16
+ "max_window_layers": 94,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 1536,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 64,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 94,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "quantization": {
28
+ "group_size": 128,
29
+ "bits": 8
30
+ },
31
+ "quantization_config": {
32
+ "group_size": 128,
33
+ "bits": 8
34
+ },
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 1000000.0,
38
+ "router_aux_loss_coef": 0.001,
39
+ "sliding_window": null,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float16",
42
+ "transformers_version": "4.51.0",
43
+ "use_cache": true,
44
+ "use_sliding_window": false,
45
+ "vocab_size": 151936
46
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59acae14769570e29aa63594d7eb8a03beba1493d7d22d3f60ae9e662b24b944
3
+ size 4942322980
model-00002-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d79ce968487f52b94a87d70e3bdab9cee6309b57b5e961b2e70b68ac5a07849
3
+ size 5131017570
model-00003-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45199901413bb03bd02ad48b85033a8071a779f9518a6a5d918d8927337ee032
3
+ size 5131017604
model-00004-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8e108fa0dfd540ed02717e3afa63d56d4ca8e0f19ce1bca8e04b50a985a5f3
3
+ size 5131017628
model-00005-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44f01448d8d5cbcc1e17b7772efc6287b7cae2cd3476feea182a0d9372477e7e
3
+ size 5131017584
model-00006-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f94c0157663a0539bcaca27363ee9da99aa6d4409defe900839adcbad369931
3
+ size 5131017685
model-00007-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd08e9efc7f9c79ef8b8d43f3fd3f4493ed757d0501bc987d23e73446622730d
3
+ size 5131017684
model-00008-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5246cb9bac3506aee1b554474b1be63f6b748106c161b0d48a084b36a071d70
3
+ size 5131017658
model-00009-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c14e96e70f4674381c08b8f8f8c717ebe24b3708bd48d471db0095a31aca5d4
3
+ size 5131017628
model-00010-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8478b47871f0378eddd98d819d7fa3fda340e783fd2dd43e97c4f24a435b6a
3
+ size 5131017642
model-00011-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9248d3710d5024e31b2de06c8c8cbf62311bb15e5c4900739a2db7450eb25e09
3
+ size 5131017606
model-00012-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ca273f7261e1742330439726efdfdf6602b66c92d9281617ed11ea16f5b6d4
3
+ size 5131017644
model-00013-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb1e1c601fddc2d0944728329bd0fb20fac481bc57835597cbbcc933a317351
3
+ size 5131017640
model-00014-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05456ac2465c58d8b7f402d099b208941976b070e087f60841218f9f8578737
3
+ size 5131017672
model-00015-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a683d0d939e677e5837d0e20a6aaa678e2fa0ad4d8be351dffdcb7c4d0aad0
3
+ size 5131017632
model-00016-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfd206a0e26786ab4ccdfb7e6ff43fe815bdcd53e38c403da0454b1a89848db
3
+ size 5131017638
model-00017-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2d3aadca7b59254bdf0cd9645017e11b5bf1b86eddb190d6f6e4bf3d93275f
3
+ size 5131017644
model-00018-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc8d7fc84f171d4bb0ee65ee6aef33a93e057387e2070e6f2eef601baca07f4
3
+ size 5131017686
model-00019-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a723b1420c68de2ac40311a94bd13198ac6fdbb00c335df93995cc13b1bea9e
3
+ size 5131017672
model-00020-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7113ff625c3de38bdb040ef12ed62aa1e12777b62530f2264d96fd60f73d1439
3
+ size 5131017692
model-00021-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896ae387c1b1b513fbf929318e4c1b16a3ba0571ae82f46c282553ffdc49b528
3
+ size 5131017686
model-00022-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf66ecbf107ae6149c80d32b049fdd50b9cc307b049288a69f30da6406ba401
3
+ size 5131017696
model-00023-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a874ae450d88b268bb112b59c02802312a0791dda03016a8aab9e908513f57
3
+ size 5131017592
model-00024-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8ed74b1fc73915b584ddc67a36be508013072ea1d18a08506b1cb280cdb531
3
+ size 5131017688
model-00025-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c0ded8592ea061c6ec1a2dfc5da6698c05142693b556ed9d2527355b0a8ed6
3
+ size 5131017634
model-00026-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405a7295898a436e66cdfee7848de2e308f8b7b65a21085bce003bba2c4cabb2
3
+ size 5131017672
model-00027-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f5ad50dbdffe853f4e6bfcbafc5f9e0e348f73c072637160ca0f1571565e19
3
+ size 5131017654
model-00028-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b0ff4701c21339724ce560964fdf1b339087121c2d43173cf36c22dc8afd4a
3
+ size 5131017654
model-00029-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:675987a84f7cf16bb0a2f40cdcdf3bd8264208253a606bc1ef2435a9c444f180
3
+ size 5131017638
model-00030-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25c1d7c3cf122e2ac4d22faaedd4b965bb5386a0fb449964565c19a3a05c0c2
3
+ size 5131017656
model-00031-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f0a0cce06cb8ec0e5534706488d6f64fae770f50939cd58299343cf8bd7f90
3
+ size 5131017636
model-00032-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c936bef13856f12073dda9a6cb007c47fc7005ce03a4c78bb3184ba4e0ab2652
3
+ size 5131017624
model-00033-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f2ef4fe683522651ae72f4934975d1b68055ea7ff0e569e108a45cd57bc746
3
+ size 5131017614
model-00034-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65127da1d692870940c45d0546a15e437684eda37e35199c93265f9ef64e213
3
+ size 5131017670
model-00035-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb67a2a4725d8c224ef3c233f09c94c370075679cf1795bfc0dd8675103bbc1
3
+ size 5131017650
model-00036-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e7a432e6eb47221c333e91f455edacb0b3a29ea3a3679ae8ae7498c4a6dc29
3
+ size 5131017670
model-00037-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0d7234641611b2595f445fedbd9c420e013429b24f2f3398498c8c1250bcea
3
+ size 5131017662
model-00038-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6584c32ca1d2adc38898143ba2643c5330c00df875b19ad00d8b1551bd3dd0ab
3
+ size 5131017650
model-00039-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f398c6a979af9a5ab7a4f4422a8564611149d6e5e4149b9d6a77cd87840123
3
+ size 5131017674
model-00040-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9c34a730385f02015416e8e78ec9ee164ef375c950e7eea0f0105aec80bd64
3
+ size 5131017632
model-00041-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b0849d594b3e6b16194df99cce7e96bfb545ef1f137dc55a62eec374c59227
3
+ size 5131017692
model-00042-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763f847f85966a8266aa8bbd31f6e730b9697f91d98f788043625f395a791297
3
+ size 5131017638
model-00043-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd4476d65fa0c89c9b6cb0d6400fd6c7ff1def6c3b64559e58ef74e043909d2
3
+ size 5131017692
model-00044-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf188d28b0df8fe77bb86b8dc597e89336a60571763deabd3607bbd0aeeb8a3
3
+ size 5131017674
model-00045-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c773e5107302f049fedd95501d265896e33f13b243fba1e664de19b0f626a2ed
3
+ size 5131017692
model-00046-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7c4bc5ec496570caeffdb5e575acbfa8b54b00c17091f6232ecc5e61720e47
3
+ size 5131017692
model-00047-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7cef7efb53c5f72eb3a76c7d6a2a34402f10f9e9f561250c5c204f7b708fe6f
3
+ size 5131017640