HF中国镜像站's logo

yifeihe3
/
phi_moe_top_4

Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
Model card Files Community
yifeihe3 commited on
Commit
1ac94b6
·
verified ·
1 Parent(s): c1531b3

Upload MixtralForCausalLM

Browse files
Files changed (37) hide show
  1. config.json +33 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00034.safetensors +3 -0
  4. model-00002-of-00034.safetensors +3 -0
  5. model-00003-of-00034.safetensors +3 -0
  6. model-00004-of-00034.safetensors +3 -0
  7. model-00005-of-00034.safetensors +3 -0
  8. model-00006-of-00034.safetensors +3 -0
  9. model-00007-of-00034.safetensors +3 -0
  10. model-00008-of-00034.safetensors +3 -0
  11. model-00009-of-00034.safetensors +3 -0
  12. model-00010-of-00034.safetensors +3 -0
  13. model-00011-of-00034.safetensors +3 -0
  14. model-00012-of-00034.safetensors +3 -0
  15. model-00013-of-00034.safetensors +3 -0
  16. model-00014-of-00034.safetensors +3 -0
  17. model-00015-of-00034.safetensors +3 -0
  18. model-00016-of-00034.safetensors +3 -0
  19. model-00017-of-00034.safetensors +3 -0
  20. model-00018-of-00034.safetensors +3 -0
  21. model-00019-of-00034.safetensors +3 -0
  22. model-00020-of-00034.safetensors +3 -0
  23. model-00021-of-00034.safetensors +3 -0
  24. model-00022-of-00034.safetensors +3 -0
  25. model-00023-of-00034.safetensors +3 -0
  26. model-00024-of-00034.safetensors +3 -0
  27. model-00025-of-00034.safetensors +3 -0
  28. model-00026-of-00034.safetensors +3 -0
  29. model-00027-of-00034.safetensors +3 -0
  30. model-00028-of-00034.safetensors +3 -0
  31. model-00029-of-00034.safetensors +3 -0
  32. model-00030-of-00034.safetensors +3 -0
  33. model-00031-of-00034.safetensors +3 -0
  34. model-00032-of-00034.safetensors +3 -0
  35. model-00033-of-00034.safetensors +3 -0
  36. model-00034-of-00034.safetensors +3 -0
  37. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MixtralForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "input_jitter_noise": 0.01,
13
+ "intermediate_size": 6400,
14
+ "lm_head_bias": true,
15
+ "max_position_embeddings": 4096,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 32,
18
+ "num_experts_per_tok": 4,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "num_local_experts": 16,
22
+ "output_router_logits": false,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 10000.0,
25
+ "router_aux_loss_coef": 0.0,
26
+ "router_jitter_noise": 0.01,
27
+ "sliding_window": 2047,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.2",
31
+ "use_cache": true,
32
+ "vocab_size": 32064
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.45.2"
6
+ }
model-00001-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d4466d673191bc9e478d6279594e9fb4aa94920191d561bb780cbcf2e6cddf
3
+ size 4992579888
model-00002-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c772c0459d31c4d22e77dc68b4c288f6dbbc592026e4c4458eb286e8cd1398c
3
+ size 4991597832
model-00003-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2f4ff84b88e4390782a380eed517a3eadf38dd1cbef1ea409a1abf6bd1de99
3
+ size 4991597832
model-00004-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1107b207d22f98a0cc5975752541937f86a0cfb4b3b3dc58c7abf5d219ffb01b
3
+ size 4991597840
model-00005-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad5245f41de5f80b87c6f53f5bd5c9f9c9e5d4b567551862d6f514f302570d0
3
+ size 4991597840
model-00006-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b309e4aa0e1a941e281c7d9dc8ef690aa8581421cb568805417d267f8c6e7d43
3
+ size 4991597840
model-00007-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827f935d90b318a9a676270e48ec4712ab526da438d18a2013dbe300d57ad466
3
+ size 4991597840
model-00008-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa85e1b897c51eace1377d8a70af9a9b836f1f1dbed7d911544a8b6394f336d
3
+ size 4991597840
model-00009-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96de725edd1fedc6223325a1321071503d927c5a5909537258ebe00565e7d2e2
3
+ size 4991597840
model-00010-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae815220a382ed354830a06a6b6635c3deb8c9c6016d453226f8f19a58f5d243
3
+ size 4991597840
model-00011-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ecbb6b083bf497c18730732875de7a4e7ab3b8ceba840dcfc62165d41dcc4b5
3
+ size 4991597872
model-00012-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe899c88a9808711a9ee04d91ad7137a6acf8c176aaa17665ea9b933b266c2a3
3
+ size 4991597904
model-00013-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30ace549d83f4f8590702130ca1d3ae1f0806ddb91a724c9e8479532b318d32
3
+ size 4991597904
model-00014-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4338c6ba513277673896f8bd00aa9208e73e7e0781909b4a1cbb78e533a3e8a
3
+ size 4991597904
model-00015-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a343504d52e49c74e7c79d95b59eafbc6cd1c53ebdc2c64197a2079290d1a02f
3
+ size 4991597904
model-00016-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd73b5274a37d01b2162ce2e44c34d41e5688351f8752fc5179f5f4c5fe431da
3
+ size 4991597904
model-00017-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa105805c2f7986e4aeaf8792eba9a4bcf3fa3992926bb355378e6ba35fc99be
3
+ size 4991597904
model-00018-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380fcec0f40ee2256d54a8ec322e12d1c4f7f1edb8d9d6817edb53d6fef4070f
3
+ size 4991597904
model-00019-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ee757ebaa412fd928e69827f0e90ae6ffc69a8b1d534b1eb2afddcb77c26f9
3
+ size 4991597904
model-00020-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b810a415e93b1a91c57965b74615213f288beb4e2f1555190fce90eb750492c
3
+ size 4991597904
model-00021-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafce0e15a194eff87a3f68e4623c0a5082a536cd9998a37cd643d6af8784521
3
+ size 4991597904
model-00022-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c1cce844743d75bdbd65cb007ed8277fb12f31e696fb78ab7759dadf2d729f
3
+ size 4995504816
model-00023-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9df539ee9cfd01fa1ec4a2864b5c893f613a1421b9ebc294a7faf0b212473a
3
+ size 4924406432
model-00024-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9c5b0c0054c8e87f4e080352aa803d6057dd199a73d235b9a969c2b0aaadc6
3
+ size 4991597888
model-00025-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487d70542399560912676046512bcaea665f10e933bcc968ff7357a4825f57bb
3
+ size 4991597888
model-00026-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3952a126931c012bea78733b8c124ce9e34cce6f4b5edf5b1c3dde1d190159c6
3
+ size 4991597888
model-00027-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10554a421d4564d53d2e503188ff7745a05d93ded47f786922ec2adc816b2a87
3
+ size 4991597888
model-00028-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6c56c87274eada26b85072202ed0b6d0de4337c891c8b9d066ed37ecb9d708
3
+ size 4991597896
model-00029-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c045ad5390e0f2c5e34d66d3f72efe1c120f79f35d9a2b469d49402efc1651
3
+ size 4991597896
model-00030-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbea3727e008d914d9830e384c5f92c1a1658d38e3ece70db034c1af049a9697
3
+ size 4991597896
model-00031-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc18c59fc5d524d8d6e7e74b167376cfab20ca62dc2dbb3efe087e91338b0659
3
+ size 4991597896
model-00032-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff64aab53b0efc47784c5b8628085ba9346abe77e8afc29d6aa5551d67f34a31
3
+ size 4991597904
model-00033-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e489c0de8b479e725f77b2fe221faa1efaca91135a8486ea26a65361b1690cc8
3
+ size 4991597904
model-00034-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01949c078f5c06fc2c28f418bbbca72d79ae3d0917f26a0639b26ea09104310
3
+ size 2832434048
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff