intervitens commited on
Commit
41481cc
·
verified ·
1 Parent(s): 54bd732

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. config.json +58 -0
  2. model-00000-of-00058.safetensors +3 -0
  3. model-00001-of-00058.safetensors +3 -0
  4. model-00002-of-00058.safetensors +3 -0
  5. model-00003-of-00058.safetensors +3 -0
  6. model-00004-of-00058.safetensors +3 -0
  7. model-00005-of-00058.safetensors +3 -0
  8. model-00006-of-00058.safetensors +3 -0
  9. model-00007-of-00058.safetensors +3 -0
  10. model-00008-of-00058.safetensors +3 -0
  11. model-00009-of-00058.safetensors +3 -0
  12. model-00010-of-00058.safetensors +3 -0
  13. model-00011-of-00058.safetensors +3 -0
  14. model-00012-of-00058.safetensors +3 -0
  15. model-00013-of-00058.safetensors +3 -0
  16. model-00014-of-00058.safetensors +3 -0
  17. model-00015-of-00058.safetensors +3 -0
  18. model-00016-of-00058.safetensors +3 -0
  19. model-00017-of-00058.safetensors +3 -0
  20. model-00018-of-00058.safetensors +3 -0
  21. model-00019-of-00058.safetensors +3 -0
  22. model-00020-of-00058.safetensors +3 -0
  23. model-00021-of-00058.safetensors +3 -0
  24. model-00022-of-00058.safetensors +3 -0
  25. model-00023-of-00058.safetensors +3 -0
  26. model-00024-of-00058.safetensors +3 -0
  27. model-00025-of-00058.safetensors +3 -0
  28. model-00026-of-00058.safetensors +3 -0
  29. model-00027-of-00058.safetensors +3 -0
  30. model-00028-of-00058.safetensors +3 -0
  31. model-00029-of-00058.safetensors +3 -0
  32. model-00030-of-00058.safetensors +3 -0
  33. model-00031-of-00058.safetensors +3 -0
  34. model-00032-of-00058.safetensors +3 -0
  35. model-00033-of-00058.safetensors +3 -0
  36. model-00034-of-00058.safetensors +3 -0
  37. model-00035-of-00058.safetensors +3 -0
  38. model-00036-of-00058.safetensors +3 -0
  39. model-00037-of-00058.safetensors +3 -0
  40. model-00038-of-00058.safetensors +3 -0
  41. model-00039-of-00058.safetensors +3 -0
  42. model-00040-of-00058.safetensors +3 -0
  43. model-00041-of-00058.safetensors +3 -0
  44. model-00042-of-00058.safetensors +3 -0
  45. model-00043-of-00058.safetensors +3 -0
  46. model-00044-of-00058.safetensors +3 -0
  47. model-00045-of-00058.safetensors +3 -0
  48. model-00046-of-00058.safetensors +3 -0
  49. model-00047-of-00058.safetensors +3 -0
  50. model-00048-of-00058.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_deepseek.DeepseekV3Config",
9
+ "AutoModel": "modeling_deepseek.DeepseekV3Model",
10
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
11
+ },
12
+ "bos_token_id": 0,
13
+ "eos_token_id": 1,
14
+ "ep_size": 1,
15
+ "first_k_dense_replace": 3,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 7168,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 18432,
20
+ "kv_lora_rank": 512,
21
+ "max_position_embeddings": 163840,
22
+ "model_type": "deepseek_v3",
23
+ "moe_intermediate_size": 2048,
24
+ "moe_layer_freq": 1,
25
+ "n_group": 8,
26
+ "n_routed_experts": 256,
27
+ "n_shared_experts": 1,
28
+ "norm_topk_prob": true,
29
+ "num_attention_heads": 128,
30
+ "num_experts_per_tok": 8,
31
+ "num_hidden_layers": 61,
32
+ "num_key_value_heads": 128,
33
+ "num_nextn_predict_layers": 1,
34
+ "q_lora_rank": 1536,
35
+ "qk_nope_head_dim": 128,
36
+ "qk_rope_head_dim": 64,
37
+ "rms_norm_eps": 1e-06,
38
+ "rope_scaling": {
39
+ "beta_fast": 32,
40
+ "beta_slow": 1,
41
+ "factor": 40,
42
+ "mscale": 1.0,
43
+ "mscale_all_dim": 1.0,
44
+ "original_max_position_embeddings": 4096,
45
+ "type": "yarn"
46
+ },
47
+ "rope_theta": 10000,
48
+ "routed_scaling_factor": 2.5,
49
+ "scoring_func": "sigmoid",
50
+ "tie_word_embeddings": false,
51
+ "topk_group": 4,
52
+ "topk_method": "noaux_tc",
53
+ "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.46.3",
55
+ "use_cache": true,
56
+ "v_head_dim": 128,
57
+ "vocab_size": 129280
58
+ }
model-00000-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc013887bcb21bded19fef7ea7588857b08e9a45f8d755875c39f273f2a0eb3b
3
+ size 11308513936
model-00001-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb236f082921349f4f98f6a4e0bee4cdcab9fd0b2c3731caa2f0552ad5ba460
3
+ size 11308513936
model-00002-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2fc3b0897f7d88db6f0e105eb4dd00556c37d0dddfc22a7d7506b65411e6b8a
3
+ size 11308513936
model-00003-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a449849cf80cb247f2981d09ab5c41d1746f96e7612977baa445f6c10ead2a
3
+ size 11308513936
model-00004-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db75e0fa4de85ff436c07c6aad5ef7fb3ade27187a3f84d61c1f9e2cb276cb6
3
+ size 11308513936
model-00005-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c1172d3611e7d9dbc0f9e4d9b3cd80f6d6b34e9cbfb5a58ce6661a92ba2166
3
+ size 11308513936
model-00006-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b6bcbcdc993cf6b3cef53195cac81ff09581b224d296f0961a60bae7793b0f
3
+ size 11308513936
model-00007-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6863b26fca65e1235f5ac0e9b3d50bc7de559f838a916c3dbc084795f001d5fd
3
+ size 11308520080
model-00008-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03cc55d822abd66d8b34b9d03c1be71a886d6f2a797a39714199d751848833e
3
+ size 11308520080
model-00009-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0080dad8318b2268af58c8b147717d17ce66b0bf9bf51c349f2189f5f0bab2f4
3
+ size 11308520080
model-00010-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc7dfb42d8e96e14bf0ae429382d856680021fa1483caf35b26917af99a328f
3
+ size 11308520080
model-00011-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a16af253fdaa85ea5fa7fafb55fc4cb0949044f58268636ce801528a97ba573
3
+ size 11308520080
model-00012-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65a68bbf14c48991d71fa2b3aa4f159b0838900c4931336d0416ab53f4eb3a1
3
+ size 11308520080
model-00013-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8f7dcff097b96d8737a40a33ea57b96558041618252c2cf8437a3836a082b6
3
+ size 11308520080
model-00014-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b33a05181d76618c094c66e7c477ef5b35368a3c499b5e4a3027ec211c2ac2
3
+ size 11308520080
model-00015-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca20f30b2abb6ee9a9036599686ed175ee8db903dc6768c89714463e71bd38a
3
+ size 11308520080
model-00016-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9f2e281e5abf79311263d6ae6fce1ed860b688df8ad07bfaac68e37669450d
3
+ size 11308520080
model-00017-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fdf9db990957a8f161cc1f9c681c41ccf41ca0de3b17d162ce10f2949b72b86
3
+ size 11308520080
model-00018-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a14da09fcd57a1f8e0c514e2748234ef7dd196a70e6c422f9d6010f7cff8b42
3
+ size 11308520080
model-00019-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3b3184ce702daf683870129fe23774eb6002496e1019bf26e9f4187c17d9ea
3
+ size 11308520080
model-00020-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7dfd0bd43af3076a793ef0dd0e4a1392e3ec823e8b2bf6283a22053c82e517
3
+ size 11308520080
model-00021-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5068796120e831f4eb122c40d5600e7a835dbedd77f8a7bc345b674bb1df7af4
3
+ size 11308520080
model-00022-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26191b46f177e7522edf6beaae399f43d6a791d697417123d86a69a44d874d98
3
+ size 11308520080
model-00023-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a688e85e4624a94e4eba0ec351855d0c4a24b6377dfc8d9111120bfb15a27a
3
+ size 11308520080
model-00024-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4846607c7a007f510db577fa759c35643ad384923252e8c4f0b105fd3503a2
3
+ size 11308520080
model-00025-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58af9ad324d9eef234e1c03b1ff2d9fa71b25b2cbe9e18a20660120ecd749418
3
+ size 11308520080
model-00026-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e735988349ecc9681dfe0ecb2b5c2cfec2c786f69917adf2adc926d9b35fcf23
3
+ size 11308520080
model-00027-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f20c58dcf9577ff22dd05e35b1edaac1c7d6957af76db6bdf2362b09eb7f059
3
+ size 11308520080
model-00028-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4865985206ac2c625f060aed67e9751cf87bef5e68816431e5e36948671ab4f8
3
+ size 11308520080
model-00029-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5032107a51079956d54a5a535379c00b0b0bcbc63c4b4e60f60426363c069fd8
3
+ size 11308520080
model-00030-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26032fccfc7eedeb8e2e6b18d93dbf82baed49c9cca21dc94c0372fed7561cbe
3
+ size 11308520080
model-00031-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250173dab1795ab91147fc1c3df5d570581caf48f2d16ac5fb031fe30408eb43
3
+ size 11308520080
model-00032-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768d0e1959246cbe0622dbd258893de27b9f49b19871937bdea6eb7abf5e1087
3
+ size 11308520080
model-00033-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd0c2a9f35e703d582ea05f2d2b317ae09b57671908c934c8eaf50e20d99f27
3
+ size 11308520080
model-00034-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45c1b0f1df319ba80c72e41fe9e8e5fdb8848aa367d0e6536f28b0d71c6ea96
3
+ size 11308520080
model-00035-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09c2e183f662c36c33f72b634d6ecaa84c1114f1a6e2ffda366995a4d981005
3
+ size 11308520080
model-00036-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9cfbf3d8333a2780e0b31ef28c85f62a111bd6972bc5d7e3f3553057e9accd
3
+ size 11308520080
model-00037-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e594aff2b6ff4b2f304c44c282267c1233c803e77ed4d2bd99b0ab97fab0500
3
+ size 11308520080
model-00038-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:356d2d17b77cf8c87b9f165b049617198f20b42f9e41f1c59bbedd85acac50bf
3
+ size 11308520080
model-00039-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:920a4ef5ae4b0ebe820e23c047d9f24e27554749efb8f3a0f815057b99765df2
3
+ size 11308520080
model-00040-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b381e22736886f283f83febc5c4e4a2e3e585d4f363aa43f4d470a723c04a882
3
+ size 11308520080
model-00041-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea4ead8096692e57315b2c53513789ed9484a831a4db55c4378e6d2d4979e1c
3
+ size 11308520080
model-00042-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc94ed67bac6e27cd1a920a6da9ccb472940634e9fc35a40ebcd18285a3e0d7a
3
+ size 11308520080
model-00043-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b23671bfd88d9326f345a2437a3b02efb9c753f1c929b9087cdaa79f426a15
3
+ size 11308520080
model-00044-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1b60e4e9d0cd41f817771ed90e225d3f94aefa2bf3bbb5654e4f618852fdab
3
+ size 11308520080
model-00045-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bddcea1d4838a608be4e1b41ef4d3fa395f0837ea59be13154bf7c79fba1d0a4
3
+ size 11308520080
model-00046-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5a985f3f272095a5f7683a26b1b1a243d3dd0051959882b6dcb0108cb309633
3
+ size 11308520080
model-00047-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0fe58bce17e630b5f650b363e55837919c94df77885cc00a3a6d1a9c1883fa
3
+ size 11308520080
model-00048-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebaa7381eb9e81b715a84779756bae4dedc0aab3b0dfa0e08431cccfa25558b
3
+ size 11308520080