kiddyboots216 commited on
Commit
3fec7b3
·
verified ·
1 Parent(s): 702bb82

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 +38 -0
  3. generation_config.json +13 -0
  4. merges.txt +0 -0
  5. model-00001-of-00095.safetensors +3 -0
  6. model-00002-of-00095.safetensors +3 -0
  7. model-00003-of-00095.safetensors +3 -0
  8. model-00004-of-00095.safetensors +3 -0
  9. model-00005-of-00095.safetensors +3 -0
  10. model-00006-of-00095.safetensors +3 -0
  11. model-00007-of-00095.safetensors +3 -0
  12. model-00008-of-00095.safetensors +3 -0
  13. model-00009-of-00095.safetensors +3 -0
  14. model-00010-of-00095.safetensors +3 -0
  15. model-00011-of-00095.safetensors +3 -0
  16. model-00012-of-00095.safetensors +3 -0
  17. model-00013-of-00095.safetensors +3 -0
  18. model-00014-of-00095.safetensors +3 -0
  19. model-00015-of-00095.safetensors +3 -0
  20. model-00016-of-00095.safetensors +3 -0
  21. model-00017-of-00095.safetensors +3 -0
  22. model-00018-of-00095.safetensors +3 -0
  23. model-00019-of-00095.safetensors +3 -0
  24. model-00020-of-00095.safetensors +3 -0
  25. model-00021-of-00095.safetensors +3 -0
  26. model-00022-of-00095.safetensors +3 -0
  27. model-00023-of-00095.safetensors +3 -0
  28. model-00024-of-00095.safetensors +3 -0
  29. model-00025-of-00095.safetensors +3 -0
  30. model-00026-of-00095.safetensors +3 -0
  31. model-00027-of-00095.safetensors +3 -0
  32. model-00028-of-00095.safetensors +3 -0
  33. model-00029-of-00095.safetensors +3 -0
  34. model-00030-of-00095.safetensors +3 -0
  35. model-00031-of-00095.safetensors +3 -0
  36. model-00032-of-00095.safetensors +3 -0
  37. model-00033-of-00095.safetensors +3 -0
  38. model-00034-of-00095.safetensors +3 -0
  39. model-00035-of-00095.safetensors +3 -0
  40. model-00036-of-00095.safetensors +3 -0
  41. model-00037-of-00095.safetensors +3 -0
  42. model-00038-of-00095.safetensors +3 -0
  43. model-00039-of-00095.safetensors +3 -0
  44. model-00040-of-00095.safetensors +3 -0
  45. model-00041-of-00095.safetensors +3 -0
  46. model-00042-of-00095.safetensors +3 -0
  47. model-00043-of-00095.safetensors +3 -0
  48. model-00044-of-00095.safetensors +3 -0
  49. model-00045-of-00095.safetensors +3 -0
  50. model-00046-of-00095.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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 262144,
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
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 5000000,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.51.0",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.51.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3d1d62e908aadfa0a17a68457930dd176a05c92a9222513831f93cc5d13527
3
+ size 4609541752
model-00002-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e546e8e7f432d50607340525337053c7eebf0b071f7b097db289b01f6cd24203
3
+ size 4975511392
model-00003-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8bb2dd0cd61f713b9a4444fdaf89ef6509d192959ba90e142efc4b49b1dd0f
3
+ size 4975511392
model-00004-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b046a5fea3b7ee0101ce199f5bdfe244c6b0c517f35b52b663735fc98eab1d25
3
+ size 4975511392
model-00005-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866210dcd3f7215d6d874360551cde76443d95fcbc4448ca38d5ccd8272c9f1f
3
+ size 4975511392
model-00006-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1d7beffd7fe814616ea538def688fd5497a9bc9216a4e45b785f83eb1fe71b
3
+ size 4975511392
model-00007-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df90e44dc8e0149eea8392988ba15e6c65f4a01a0e2d34acd6c9f4990a9110c2
3
+ size 4975511392
model-00008-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6546bb1cc69b8b090859d3b50d7af7eaa6f2f36368bec1ad8c12bfc2529f00
3
+ size 4975511392
model-00009-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1331254b548ec59c438f6ff336add43d23f1b2119ac3d0145df53fe8266ea958
3
+ size 4975511392
model-00010-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10dd65bb1cb4c142e90e599ed217158b3bbb9cb05780fb335b6b0b7b9ccc5f69
3
+ size 4975511392
model-00011-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa83e6078d15ba7b8eee1767ad2cfa8de814da9ca325d9cfc4a508ffff2b2c24
3
+ size 4975511408
model-00012-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ab7c23a4fcdd755ab039ee37e5e51cd74959f20d0675450f6b92cdb4e92ad6
3
+ size 4975511400
model-00013-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a277888ebc0a09f9a407f46adf931eed4a90d823c96cf799eec8f2310e72c918
3
+ size 4975511400
model-00014-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185e819c7c92853cd82ad0d6df8065d2ce6490f6287eb96c53dff7125295c277
3
+ size 4975511400
model-00015-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb17c31f9351c3e8fe2c11f2d42219fff8753a4eadd51c60ea7165b6bca9919c
3
+ size 4975511400
model-00016-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be04b6cb46ac69b524f1873771f2de9501f99aa97b553e33d8743f5cb5ddb8c
3
+ size 4975511400
model-00017-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2583a233ff10b52568281941a5021c16a47279d287036fec10871a8ea8b18ab8
3
+ size 4975511400
model-00018-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3921cf034fd4bbad2c78e2265411313f8a4a59274bc61f27ae267ba6ea686d88
3
+ size 4975511400
model-00019-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba35e99a58dea5f6a3fb05ee9076378db92daf37e13d44a7cf0c5660582e20e
3
+ size 4975511400
model-00020-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e683fb192b4b956c6a67a836de3d4a128c6a836180ff99afcec449462f131ef
3
+ size 4975511400
model-00021-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6775a82a3a88817e4968713bf4f7853dbc1b11494402466f1c6c9bc601ed1c7b
3
+ size 4975511400
model-00022-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b052db87dde47a1b903b0a95d42f5c6d30f7cc3bab12d93ea6413c62ad35a92
3
+ size 4975511400
model-00023-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b50e20d8e45605dd818e666a6429339adcfc9b4f9350025cb665922b35e125b8
3
+ size 4975511400
model-00024-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec714e5ec585726bce9f98f63db5fbace6c61f2b6fd6597d4b6c996aebebd85
3
+ size 4975511400
model-00025-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c718225a6699b88ec037b83cb36209e457c9216c756f32fff42d67e620439f16
3
+ size 4975511400
model-00026-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8586a1a6623eb6b3d8336bd87e57b02d2ab0c93f217cab6d8345b03bd8e7b050
3
+ size 4975511400
model-00027-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10d6bb5b334cd7ac22dd6f0d6eeabd52fa6fc3a2201a6af52ed79dbc0728ea9a
3
+ size 4975511400
model-00028-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76357f9955fe299eb90bd75fcbe1dd1cb8861845d414cb8866034d9eb50b48f7
3
+ size 4975511400
model-00029-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc10a41a5b3abdc53810c226479e4e0dffa5ece6744f11a55fb16a9f808bde2
3
+ size 4975511400
model-00030-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d56e243296b844062b2b5a08805e6ba30ebaf7b716a01e36a2fd88a6c8e3015d
3
+ size 4975511400
model-00031-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c01496ffb9807ac54d778d5235e8be927cbcd3a6d848886bc5a0f54494254f
3
+ size 4975511400
model-00032-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a75aea2e1ef7e644ea99286d15e022b0be2c6fef857944bbf708e1b7fc5c248
3
+ size 4975511400
model-00033-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd69626bf3efdf9f555994b79a95accdc1d8159cd6040b6fe09bb0c7f67cdc0
3
+ size 4975511400
model-00034-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a110da5a5d92e712f31081cbff1c2bccd9b66cbc49e4fca6a7866fea1d1980
3
+ size 4975511400
model-00035-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a5263f35ab9ced4500c47fe8aa34dac8733071e0effdc4abdaa03bbc81018f2
3
+ size 4975511400
model-00036-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa5b8cfadf53970dbd9687706bbfe178bccf6c81c21f91bfdb5e577fc4c2fc1
3
+ size 4975511400
model-00037-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d48d1c5baad1f8ce3ec9f1abcbb6f2c1c735f16670d0b44a69f920ad220eb9b4
3
+ size 4975511400
model-00038-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af9eb9822cb1b91509da2f96cf4be79857442f92382b0516e7f73d6edcb54c4
3
+ size 4975511400
model-00039-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e679dce295d553098ec60f165e8e7354d4170c5504c56802cafcd7a007217e1
3
+ size 4975511400
model-00040-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab2f1e7d52f59c89332de57c00ef926589a1abeb5961884e40f3eb6ac1679bb
3
+ size 4975511400
model-00041-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b4025438d0025f84a9ab6ef7bf895fc336dc6766a7ec3206df4058c15e7825
3
+ size 4975511400
model-00042-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99ee2fc4a0c4ad631c07ab8db8b3cc05a13533bfab3a084bf4a7fe8d650b295
3
+ size 4975511400
model-00043-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e540a297180c27dc7f4a6c0e2c58b8a36ce2b73ebc6ba460e2d6c6a31b234e
3
+ size 4975511400
model-00044-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3724bd32732c3c67c44e384a0515d6c00db7221a9ce6f5a4fdb0d28672ba34d2
3
+ size 4975511400
model-00045-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca1b8ce92f37acd6a73fa8c93af775983e698d87ae7a08149819fffad143fe6
3
+ size 4975511400
model-00046-of-00095.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5755ca9cff485a37025894ae60473aa520ee6abd996969e6d4b30c8b5b6e86
3
+ size 4975511400