rhuanmatias commited on
Commit
5633fa9
·
verified ·
1 Parent(s): fe86672

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 +2 -0
  2. config.json +66 -0
  3. generation_config.json +9 -0
  4. model-00001-of-000163.safetensors +3 -0
  5. model-00002-of-000163.safetensors +3 -0
  6. model-00003-of-000163.safetensors +3 -0
  7. model-00004-of-000163.safetensors +3 -0
  8. model-00005-of-000163.safetensors +3 -0
  9. model-00006-of-000163.safetensors +3 -0
  10. model-00007-of-000163.safetensors +3 -0
  11. model-00008-of-000163.safetensors +3 -0
  12. model-00009-of-000163.safetensors +3 -0
  13. model-00010-of-000163.safetensors +3 -0
  14. model-00011-of-000163.safetensors +3 -0
  15. model-00012-of-000163.safetensors +3 -0
  16. model-00013-of-000163.safetensors +3 -0
  17. model-00014-of-000163.safetensors +3 -0
  18. model-00015-of-000163.safetensors +3 -0
  19. model-00016-of-000163.safetensors +3 -0
  20. model-00017-of-000163.safetensors +3 -0
  21. model-00018-of-000163.safetensors +3 -0
  22. model-00019-of-000163.safetensors +3 -0
  23. model-00020-of-000163.safetensors +3 -0
  24. model-00021-of-000163.safetensors +3 -0
  25. model-00022-of-000163.safetensors +3 -0
  26. model-00023-of-000163.safetensors +3 -0
  27. model-00024-of-000163.safetensors +3 -0
  28. model-00025-of-000163.safetensors +3 -0
  29. model-00026-of-000163.safetensors +3 -0
  30. model-00027-of-000163.safetensors +3 -0
  31. model-00028-of-000163.safetensors +3 -0
  32. model-00029-of-000163.safetensors +3 -0
  33. model-00030-of-000163.safetensors +3 -0
  34. model-00031-of-000163.safetensors +3 -0
  35. model-00032-of-000163.safetensors +3 -0
  36. model-00033-of-000163.safetensors +3 -0
  37. model-00034-of-000163.safetensors +3 -0
  38. model-00035-of-000163.safetensors +3 -0
  39. model-00036-of-000163.safetensors +3 -0
  40. model-00037-of-000163.safetensors +3 -0
  41. model-00038-of-000163.safetensors +3 -0
  42. model-00039-of-000163.safetensors +3 -0
  43. model-00040-of-000163.safetensors +3 -0
  44. model-00041-of-000163.safetensors +3 -0
  45. model-00042-of-000163.safetensors +3 -0
  46. model-00043-of-000163.safetensors +3 -0
  47. model-00044-of-000163.safetensors +3 -0
  48. model-00045-of-000163.safetensors +3 -0
  49. model-00046-of-000163.safetensors +3 -0
  50. model-00047-of-000163.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ *.pdf filter=lfs diff=lfs merge=lfs -text
37
+ *.png filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV32ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "ep_size": 1,
10
+ "first_k_dense_replace": 3,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 7168,
13
+ "index_head_dim": 128,
14
+ "index_n_heads": 64,
15
+ "index_topk": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 18432,
18
+ "kv_lora_rank": 512,
19
+ "max_position_embeddings": 163840,
20
+ "model_type": "deepseek_v32",
21
+ "moe_intermediate_size": 2048,
22
+ "moe_layer_freq": 1,
23
+ "n_group": 8,
24
+ "n_routed_experts": 256,
25
+ "n_shared_experts": 1,
26
+ "norm_topk_prob": true,
27
+ "num_attention_heads": 128,
28
+ "num_experts_per_tok": 8,
29
+ "num_hidden_layers": 61,
30
+ "num_key_value_heads": 128,
31
+ "num_nextn_predict_layers": 1,
32
+ "q_lora_rank": 1536,
33
+ "qk_nope_head_dim": 128,
34
+ "qk_rope_head_dim": 64,
35
+ "quantization_config": {
36
+ "activation_scheme": "dynamic",
37
+ "fmt": "e4m3",
38
+ "quant_method": "fp8",
39
+ "scale_fmt": "ue8m0",
40
+ "weight_block_size": [
41
+ 128,
42
+ 128
43
+ ]
44
+ },
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": {
47
+ "beta_fast": 32,
48
+ "beta_slow": 1,
49
+ "factor": 40,
50
+ "mscale": 1.0,
51
+ "mscale_all_dim": 1.0,
52
+ "original_max_position_embeddings": 4096,
53
+ "type": "yarn"
54
+ },
55
+ "rope_theta": 10000,
56
+ "routed_scaling_factor": 2.5,
57
+ "scoring_func": "sigmoid",
58
+ "tie_word_embeddings": false,
59
+ "topk_group": 4,
60
+ "topk_method": "noaux_tc",
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.44.2",
63
+ "use_cache": true,
64
+ "v_head_dim": 128,
65
+ "vocab_size": 129280
66
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "do_sample": true,
6
+ "temperature": 1.0,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.46.3"
9
+ }
model-00001-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b449b3cbe82bdfec0f92ba0a36508796c9a0d4123c72ee3e889979c52a7827
3
+ size 6715943381
model-00002-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4313715a172c67182e26a74a4631468b327141ccd3de9ff08fbced1581b7ae
3
+ size 2420611708
model-00003-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2191a61f074266b2bd76fa9da54e44aaa3f38b2d23c7c3ca7c23a9648ba8f9b3
3
+ size 2420612117
model-00004-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5a804858a376319e8e2ebfbec9f47626784413d255a50326c9b53c302f837c
3
+ size 2566898496
model-00005-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3efa0e1641a670e35cf09709fde153807db073ffab71c27c7a736bea1fa5a8
3
+ size 2420611898
model-00006-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf62876b7b623ff5d0c84431013730cf7a98111676208f3ddc49f106eca2ea0
3
+ size 2444866253
model-00007-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57d8f557f16f6a02837f2752d11ffda82c8eca6c83e4566bc8c7de621959d41
3
+ size 2550905660
model-00008-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1e2609398992411229bc89a8a7b302ad186ca4ded4d5e7e0dda545eba1268d8
3
+ size 2420612086
model-00009-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5f4291e94be095e26103a2977cd7302e5b13c76685930d576112522cf94c84
3
+ size 2566898702
model-00010-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9521273869e10009a600b51da01f85fe30d71ff71c3847e0bb56e096a9f75b5a
3
+ size 2420611690
model-00011-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11612135d4eb894e5f847911e97520d8e7987a551dca405bae61b24ad3895098
3
+ size 2420612123
model-00012-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae40d73c70773edaa79895c8db65556bd6a469e8b02c3fe53c9c0a55a9b94ed
3
+ size 834470067
model-00013-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bbd7cfb5a6f9495242a9ea712df6e28d17fe828edae8908984aa07cf278ea4
3
+ size 2566836935
model-00014-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6e792bd167f775653975387a08bf53c5e98064ea979613ac2ef1af5b4b53f7
3
+ size 2420612080
model-00015-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:237dbf34388dc79984b9da5f9c57a60b816c090c2a09792de5a99b1e549a68fa
3
+ size 2566898714
model-00016-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2b061ebefd960ad28305cc0d692f1c47c9e0e124ef31bde03a8fa2128f93e6
3
+ size 2420611682
model-00017-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2224d726a6304e3ff1fe3b80641b0585ae03331e7d6e0719bfb47201db1781
3
+ size 2420612121
model-00018-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6bcb347ef191e2185a904d3cb3c646f32feeb7019d470649abc9fc2e2ede083
3
+ size 2566898520
model-00019-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f06d00eb77e6bad3ed6ec1617c3c885cb16dccd5328d02c735c6f2692bdd97
3
+ size 2420611870
model-00020-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db51852313b08800807e25d56e60844fed9d4711bfb5d285e34abcdb0d6d16d
3
+ size 2420612123
model-00021-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8725daedf27052f829aa918a1466d4efad9953ed4013db34e329794b2a5b0e
3
+ size 2566898910
model-00022-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f2edd41df0f4f468c0807d8140a04830691fab6db8bc5f19d8b70c5d0de6d4
3
+ size 2420612642
model-00023-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423b6f3ec0dd9edcb9c57af1bf41adfa724c0c37026acdcc9bde8636efba5934
3
+ size 2566899313
model-00024-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f7700d780a99514e0d76d7ff3ab6ff4c0674c6a91655ef7d456cc6f855d875
3
+ size 2420612246
model-00025-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee165165fa09d8de832f139f356984ea2d53e5d1e141ce18d121ab4d28acc640
3
+ size 2420612709
model-00026-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a201754686b1cec24b96bc5f18eeb2bec7c35a89ebc2bfefdca7ef2e45c85aaf
3
+ size 2566899127
model-00027-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423c79026f04792f13facb8aa6dde92cc488e48a3120b37dfafb80dd8b573f0f
3
+ size 2420612432
model-00028-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd9d4c046fbbda7ceb38d3e3e2e2c62d935c6a3e0fe238d45e0fd32d6dae6f55
3
+ size 2420612703
model-00029-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3abf70e8f69286db3556b4e0ed4f88849b39cf0092373251427d901f5bef35
3
+ size 2566898939
model-00030-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7507b82f45d0c95b336346395c9151c8e850dad185dde5455d2aa0bd4886fc48
3
+ size 2420612622
model-00031-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e0cfab7285892ce2c1b01aaaa3cfe9a9b83c5764662b955bfcd66d0478f0a2
3
+ size 2566899339
model-00032-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c75b065d4d3cf08447b8665914ee9224b423fa9dc05400df67a32625ade9689
3
+ size 2420612222
model-00033-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5994391ce52e78fb72a2b017e7251eba0f202dd0bf65aa62e3aafd24a79412e3
3
+ size 2420612703
model-00034-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e8ddea67c12262634ddd56aac877887bd5dde92a1c6759c9aefe24b7b4aea90
3
+ size 1049268639
model-00035-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ddeb879462d57d1cacf0ae97571c96fcb807594a904f093f381cb8b6ba0abc
3
+ size 2566837513
model-00036-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd6c5ce29943977bfc34af5a8074bbd41458f1879af6c0e1aaa6c773cd416c6f
3
+ size 2420612666
model-00037-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2790aba7c653a2e9336f7d2c094bb8560894757d5221cc9cae2b6413be41f662
3
+ size 2566899295
model-00038-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057a896e6390522d0accaf08d83eb077f5e1c1c85cc528fe98ee3a6deea24381
3
+ size 2420612268
model-00039-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81db8be260c6fb8211fa31d6130f69f38227423b8daa7a4ec5dc39c599c400d
3
+ size 2420612707
model-00040-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8c19ac25941a395d353af090d7aacc985f1c04aaf5488f7e413684963c6e17
3
+ size 2566899101
model-00041-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f43c7dbc6deefae73c7bf3d0a6a88542df87819a22ff551e6146e250fc8599a
3
+ size 2420612456
model-00042-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098c3ff60b60b6b6fb9ee43e928e2671eefd58b1de63de065e6acefc019f9a3d
3
+ size 2420612709
model-00043-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c08aecec28fecdd56ed33d6edeb40d03fa9e3a45999c373c26cb15f3f8e995
3
+ size 2566898915
model-00044-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2972ae5739ebb1c1996e0370f8fb0de80a4ed328d17ee148b577e5bf8eb3b84e
3
+ size 2420612642
model-00045-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b66538455d0eef9b6453ab6be1545cc9a553d9b483e9e0cd427da8bfd1fe3a35
3
+ size 2566899313
model-00046-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bebc9db743da3871be0318fa835a849397f4396e87850378cb1e50fb1b0c2cb
3
+ size 2420612246
model-00047-of-000163.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1509765b4f8d92fcdb335ee4457b6ac1a0eba68c6f8cb441cb77b500f536043c
3
+ size 2420612709