Hugging Face's logo

cloudyu
/
Llama-3-70Bx2-MOE

Text Generation
Transformers
Safetensors
mixtral
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
cloudyu commited on
Commit
c7d8768
•
1 Parent(s): 0db7835

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 +35 -0
  2. model-00001-of-00052.safetensors +3 -0
  3. model-00002-of-00052.safetensors +3 -0
  4. model-00003-of-00052.safetensors +3 -0
  5. model-00004-of-00052.safetensors +3 -0
  6. model-00005-of-00052.safetensors +3 -0
  7. model-00006-of-00052.safetensors +3 -0
  8. model-00007-of-00052.safetensors +3 -0
  9. model-00008-of-00052.safetensors +3 -0
  10. model-00009-of-00052.safetensors +3 -0
  11. model-00010-of-00052.safetensors +3 -0
  12. model-00011-of-00052.safetensors +3 -0
  13. model-00012-of-00052.safetensors +3 -0
  14. model-00013-of-00052.safetensors +3 -0
  15. model-00014-of-00052.safetensors +3 -0
  16. model-00015-of-00052.safetensors +3 -0
  17. model-00016-of-00052.safetensors +3 -0
  18. model-00017-of-00052.safetensors +3 -0
  19. model-00018-of-00052.safetensors +3 -0
  20. model-00019-of-00052.safetensors +3 -0
  21. model-00020-of-00052.safetensors +3 -0
  22. model-00021-of-00052.safetensors +3 -0
  23. model-00022-of-00052.safetensors +3 -0
  24. model-00023-of-00052.safetensors +3 -0
  25. model-00024-of-00052.safetensors +3 -0
  26. model-00025-of-00052.safetensors +3 -0
  27. model-00026-of-00052.safetensors +3 -0
  28. model-00027-of-00052.safetensors +3 -0
  29. model-00028-of-00052.safetensors +3 -0
  30. model-00029-of-00052.safetensors +3 -0
  31. model-00030-of-00052.safetensors +3 -0
  32. model-00031-of-00052.safetensors +3 -0
  33. model-00032-of-00052.safetensors +3 -0
  34. model-00033-of-00052.safetensors +3 -0
  35. model-00034-of-00052.safetensors +3 -0
  36. model-00035-of-00052.safetensors +3 -0
  37. model-00036-of-00052.safetensors +3 -0
  38. model-00037-of-00052.safetensors +3 -0
  39. model-00038-of-00052.safetensors +3 -0
  40. model-00039-of-00052.safetensors +3 -0
  41. model-00040-of-00052.safetensors +3 -0
  42. model-00041-of-00052.safetensors +3 -0
  43. model-00042-of-00052.safetensors +3 -0
  44. model-00043-of-00052.safetensors +3 -0
  45. model-00044-of-00052.safetensors +3 -0
  46. model-00045-of-00052.safetensors +3 -0
  47. model-00046-of-00052.safetensors +3 -0
  48. model-00047-of-00052.safetensors +3 -0
  49. model-00048-of-00052.safetensors +3 -0
  50. model-00049-of-00052.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 64,
18
+ "num_experts_per_tok": 2,
19
+ "num_hidden_layers": 80,
20
+ "num_key_value_heads": 8,
21
+ "num_local_experts": 2,
22
+ "output_router_logits": false,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 500000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "router_jitter_noise": 0.0,
29
+ "sliding_window": null,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.41.0",
33
+ "use_cache": true,
34
+ "vocab_size": 128256
35
+ }
model-00001-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f84d1ed4e9edf87a8456822c68da25e4c670b2941eeed9603efb4c10a53df5c
3
+ size 4752180696
model-00002-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507ae383ed4917dcf01c139d4d940f18e91c0be23dc4a8216eeaa79433ef0606
3
+ size 4831906352
model-00003-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a4420b23749b458fcac2cf9d020eee217f242593bb8b2b06481bd6a7515e86
3
+ size 4999661672
model-00004-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29497a1a350a1f20fc8251baf573037ae474805641f81b1787d6a44fb4f82506
3
+ size 4831889856
model-00005-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667577c7085cb279adce41b71bf5f41e0de2805029ad7ddba0f752729fcf8bf
3
+ size 4831906352
model-00006-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00414498400568c9d79a5d14bb3f881babb544a14d5637fa1c61ff228126a8e7
3
+ size 4999645176
model-00007-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3de6a81a65b6288b0289837f6e50b52fcb8a1b7e822161e569131b70b1e4fa2
3
+ size 4831906352
model-00008-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c51ab86902cedcc16f4b7ab9e773fdfb74244dd175efe5e9ff44410cdf5849c
3
+ size 4999645192
model-00009-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cecfd9aab85eefd6a80df7f1d55c107974ccca7be37e8e76bc6411b4a91c6877
3
+ size 4831906376
model-00010-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ec0574bd9b4cea51e9a323e2fdf893edb5f766c9935e34920919ffd362e5db
3
+ size 4999661688
model-00011-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9598b3c544877f6b06ae991228332d8963e4772ed183651d82abdf08856dd632
3
+ size 4831889880
model-00012-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab027585ccd366c1b4d0f3bcb02fb9e2baf70c0c2b15e1144f3716487a3083a
3
+ size 4831906376
model-00013-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a94a5bae8a9f3f959c835f412b0292e7336b9736862f1bcb40eb6bf81ae008
3
+ size 4999645192
model-00014-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef7e280ded0f6396514be2a5502f0eb74dca884dc7ceb45fa10bbdff062ae0a
3
+ size 4831906376
model-00015-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757bc886c2a76bb9aa563e04ade6f732734a7dc64ebf72c75fce015cf70ac2a7
3
+ size 4999645192
model-00016-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f728874aacf6ad51b4bc5e07bf5909b90bcad37c80b19cdde3f1fb540e211226
3
+ size 4831906376
model-00017-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12dc630cc920da38d8f12bd82ab28845c31526a288cde00172c6bbba8cc54125
3
+ size 4999661688
model-00018-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c592df6c5868a781caa08b977a12a0bf0719ec2d72696debeb090442fc0f2aea
3
+ size 4831889880
model-00019-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe474d78d43d38e8dba1ad00d55ba6a49cc2f755307a7a3f80d95d86bc39b70
3
+ size 4831906376
model-00020-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add71f63e4aec5deea397b52c9a765af7417a98d0b84d2124d92feec76afac87
3
+ size 4999645192
model-00021-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b80e3662818d00cc4012dfa52d2056e8bbcd8c91a813628b05c48ace497b24
3
+ size 4831906376
model-00022-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37af55b05ead58de864b299ed26e29f1fa95866d1277f337fb4d29331c2d4184
3
+ size 4999645192
model-00023-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0172ccb6ffbb4fe6dae4f32c8c78292103d578b6b0fe675c5a019c2a20fdf94a
3
+ size 4831906376
model-00024-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c496d22cedab191315df7c2f78c576799e4d7bc437a6a0d11c225f7af64976
3
+ size 4999661688
model-00025-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa802421d5edf8b71d9a2df09384e7682d97913e2e00d73c2706df8c0ca13cb
3
+ size 4831889880
model-00026-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6521ee721bde2b8a7874db5740568ec05010b54ac82d1552dd0924a134a12e
3
+ size 4831906376
model-00027-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11664e8c4689ba2fbc70f31b816c61db0e67006142509ff46bf04ee30d607c9d
3
+ size 4999645192
model-00028-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8008a4a730ac293409fdb6ddeb50a455842694e4efd16738469abe019d9b4f1d
3
+ size 4831906376
model-00029-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1bb28986767306359a09978f96855e029a846901f47156072c898a0bbf450a1
3
+ size 4999645192
model-00030-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed3f517437f8561e672cedf8939d8556b96a1c8aef0c87517d33e7550746b30
3
+ size 4831906376
model-00031-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedf1b873a873ce41d12365f970c30cc6311b4d3f66d62b2dc24ad7a3fbec34b
3
+ size 4999661688
model-00032-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ad2f496bfcdd5312e91fe34bc21c0a2c71e69fc755ea03c59e333ce700937c
3
+ size 4831889880
model-00033-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3f4859ccafaf3b601a82343f5cb7ebe0355b45b2bcd04ef98dc6d54bf98c85
3
+ size 4831906376
model-00034-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ae5303f0160d88586c5ef6b08aae7288f86b6aabbdd9d5529b0c66387753c0
3
+ size 4999645192
model-00035-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede5e0915b1c6f37163f22f6260c5ad58052a4ca1b9166f9add17ea987ff0226
3
+ size 4831906376
model-00036-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc88a277a1373897aa795e45c48eaea49c75cdb275a9d57eab4075b2563c20db
3
+ size 4999645192
model-00037-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:effdea5d143fc8a4f297fc4cf81430b3e624a9a0574084ebcf45792c2c9e24ac
3
+ size 4831906376
model-00038-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d46f842c11320d4295c57add7c75d0f2435015262c33894a4cea71febcc853
3
+ size 4999661688
model-00039-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d30b82ad8c74402bae7398b23afc06277afc10983c53d4a546e0952c26b2223
3
+ size 4831889880
model-00040-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bc64dc26f61ee726fb4a00a8795d0c694b46bcf32bec75e49dd3a78b7ce896
3
+ size 4831906376
model-00041-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5996314b3babff8aee33835a13e0c2f2cefa377549e19e6d6a48d64f383d71c0
3
+ size 4999645192
model-00042-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c4b6e087f22d79333ff54d943a10e59bf83d81bc37df65ac36b0e4fa950a69
3
+ size 4831906376
model-00043-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d50f40c65d2c23b233f6f930192fa35050eda257b1855f2e95a6efe0be89d8
3
+ size 4999645192
model-00044-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c658cb3924dacfbbe76fdd46563fe8aafe508cbc6174430e85d37c80af3dc818
3
+ size 4831906376
model-00045-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f8c06aba922be3f201298c2ecb74da34908bc1f1a0da514a4fb7d1ee4b1f20
3
+ size 4999661688
model-00046-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c6f1492e8be6b6b056cfc5115e2c6311df49280c7ec79fbbe50f6e528bb849
3
+ size 4831889880
model-00047-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e48cba90ec0b32e3a6e4ec802699f3fc5cdc8b91140420dbd5be9f8218bab77
3
+ size 4831906376
model-00048-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb059c0aa4d2d845bdb07eb2e5fc71d2bafcbd97aa01b8daa2b2af46a64ac62
3
+ size 4999645192
model-00049-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4775822b061805f327b54241841feb598b8e4da7b0ffae23dcf57051c9bf9556
3
+ size 4831906376