Hugging Face's logo

lisali126
/
light-fairseq-moe-52b

Transformers
PyTorch
English
fairseq-moe
Inference Endpoints
Model card Files Community
lisali126 commited on
Commit
bc764f3
·
1 Parent(s): 7600a51

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 +2 -1
  2. generation_config.json +1 -1
  3. pytorch_model-00001-of-00129.bin +3 -0
  4. pytorch_model-00002-of-00129.bin +3 -0
  5. pytorch_model-00003-of-00129.bin +3 -0
  6. pytorch_model-00004-of-00129.bin +3 -0
  7. pytorch_model-00005-of-00129.bin +3 -0
  8. pytorch_model-00006-of-00129.bin +3 -0
  9. pytorch_model-00007-of-00129.bin +3 -0
  10. pytorch_model-00008-of-00129.bin +3 -0
  11. pytorch_model-00009-of-00129.bin +3 -0
  12. pytorch_model-00010-of-00129.bin +3 -0
  13. pytorch_model-00011-of-00129.bin +3 -0
  14. pytorch_model-00012-of-00129.bin +3 -0
  15. pytorch_model-00013-of-00129.bin +3 -0
  16. pytorch_model-00014-of-00129.bin +3 -0
  17. pytorch_model-00015-of-00129.bin +3 -0
  18. pytorch_model-00016-of-00129.bin +3 -0
  19. pytorch_model-00017-of-00129.bin +3 -0
  20. pytorch_model-00018-of-00129.bin +3 -0
  21. pytorch_model-00019-of-00129.bin +3 -0
  22. pytorch_model-00020-of-00129.bin +3 -0
  23. pytorch_model-00021-of-00129.bin +3 -0
  24. pytorch_model-00022-of-00129.bin +3 -0
  25. pytorch_model-00023-of-00129.bin +3 -0
  26. pytorch_model-00024-of-00129.bin +3 -0
  27. pytorch_model-00025-of-00129.bin +3 -0
  28. pytorch_model-00026-of-00129.bin +3 -0
  29. pytorch_model-00027-of-00129.bin +3 -0
  30. pytorch_model-00028-of-00129.bin +3 -0
  31. pytorch_model-00029-of-00129.bin +3 -0
  32. pytorch_model-00030-of-00129.bin +3 -0
  33. pytorch_model-00031-of-00129.bin +3 -0
  34. pytorch_model-00032-of-00129.bin +3 -0
  35. pytorch_model-00033-of-00129.bin +3 -0
  36. pytorch_model-00034-of-00129.bin +3 -0
  37. pytorch_model-00035-of-00129.bin +3 -0
  38. pytorch_model-00036-of-00129.bin +3 -0
  39. pytorch_model-00037-of-00129.bin +3 -0
  40. pytorch_model-00038-of-00129.bin +3 -0
  41. pytorch_model-00039-of-00129.bin +3 -0
  42. pytorch_model-00040-of-00129.bin +3 -0
  43. pytorch_model-00041-of-00129.bin +3 -0
  44. pytorch_model-00042-of-00129.bin +3 -0
  45. pytorch_model-00043-of-00129.bin +3 -0
  46. pytorch_model-00044-of-00129.bin +3 -0
  47. pytorch_model-00045-of-00129.bin +3 -0
  48. pytorch_model-00046-of-00129.bin +3 -0
  49. pytorch_model-00047-of-00129.bin +3 -0
  50. pytorch_model-00048-of-00129.bin +3 -0
config.json CHANGED
@@ -4,6 +4,7 @@
4
  "architectures": [
5
  "FSGPTMoEForCausalLM"
6
  ],
 
7
  "attention_dropout": 0.1,
8
  "attention_heads": 16,
9
  "batch_prioritized_routing": false,
@@ -28,7 +29,7 @@
28
  "pad_token_id": 50258,
29
  "resid_dropout": 0.1,
30
  "router_bias": false,
31
- "router_dtype": "float32",
32
  "router_ignore_padding_tokens": true,
33
  "second_expert_policy": "all",
34
  "sparse_step": 2,
 
4
  "architectures": [
5
  "FSGPTMoEForCausalLM"
6
  ],
7
+ "model_type": "fairseq-moe",
8
  "attention_dropout": 0.1,
9
  "attention_heads": 16,
10
  "batch_prioritized_routing": false,
 
29
  "pad_token_id": 50258,
30
  "resid_dropout": 0.1,
31
  "router_bias": false,
32
+ "router_dtype": "bfloat16",
33
  "router_ignore_padding_tokens": true,
34
  "second_expert_policy": "all",
35
  "sparse_step": 2,
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 50257,
4
  "eos_token_id": 50259,
5
  "pad_token_id": 50258,
6
- "transformers_version": "4.34.1"
7
  }
 
3
  "bos_token_id": 50257,
4
  "eos_token_id": 50259,
5
  "pad_token_id": 50258,
6
+ "transformers_version": "4.35.2"
7
  }
pytorch_model-00001-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86601ee8a46846d71645d06d7958b59d38b1a0b93ef2b1b7d3c0ff99b697ada1
3
+ size 805863719
pytorch_model-00002-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c71e90696aedaa0e2a6745e69c4f49941a40624a411c0edb8351f21d7a019e8
3
+ size 805863719
pytorch_model-00003-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc401f17791cdf22626866d1748d44594a51938fd7c850b293e75defecb99089
3
+ size 805863783
pytorch_model-00004-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0968d478fd16d8b57ff1b6c9ffa5b337e5111ef34802dff5e0905d9c62e66b
3
+ size 805863911
pytorch_model-00005-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57be95afaee854d5dfaadec6f95ddab45935aee8cc3991b73fa0b6822ddf2907
3
+ size 805863911
pytorch_model-00006-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f05157c4514d68c786cf5aa1636714040992b1d21798b57f806cf1443d3376a
3
+ size 805863911
pytorch_model-00007-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85726e3a23a92154d13c018401b00114049a98c3d1b56c249b6f9ec85883c32d
3
+ size 805863911
pytorch_model-00008-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c689c11f2da39d0d855a8ac8ff0278bc695957b1a54ebb6ed46a1ec88166d4
3
+ size 805863911
pytorch_model-00009-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e455418ac3cc296e344286a915febd3259fd9ffc548076387b4ef735af0c4ef
3
+ size 805863911
pytorch_model-00010-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:344f01ee728c6ddc6cdf5bcc87629bdf8e2d42d1f7639a09e6056e291481cadc
3
+ size 805863911
pytorch_model-00011-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e867474f1e4e69dddd729b84dc3fbed76abca66ce68b5856f1332bcc68b86e96
3
+ size 805863911
pytorch_model-00012-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d46c82ff17f0bee7509773236c0333c7b64cce27b63d1fc9072c55fd7ad41e2
3
+ size 805863911
pytorch_model-00013-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d845d981401980c86847a505ae39f1362070a40ce4ce35f1b499fa3ae678de46
3
+ size 805863911
pytorch_model-00014-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9974bc4a62178dd2da3a0ce2c75ce148e86b740e8c4d7ff30ffe5db57649bc2b
3
+ size 805863911
pytorch_model-00015-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca956683ca9e7b4949cf7623c182333367c4f67da3066187f75bb75452188392
3
+ size 805863911
pytorch_model-00016-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83379b28761925cc4f08468135a09423a91444c56531b7c628b6342845fd1f9e
3
+ size 805863911
pytorch_model-00017-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e38f88c719432807a4d510b3784be867ab77fe9c9f4815d7ce84cc3866f6ab07
3
+ size 805863911
pytorch_model-00018-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed47c602051553a1bd96c8647a8a5fcb5639a54ae3bff19392ed6638e133f79f
3
+ size 805863911
pytorch_model-00019-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e31bae07b5f2a69fbb2aab80949993550fcb6a38d1a130b6965a259d664644
3
+ size 805863911
pytorch_model-00020-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925f232df288b51a24bc1b30d0310bcceb081838c466967db8a5e6113d0f2583
3
+ size 805863911
pytorch_model-00021-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e661a80c042a189159c81c29bd234f878313d6ae522d19b303379011a11d6f5
3
+ size 805863911
pytorch_model-00022-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5498281cf04bd187490f0d4334852e0d4ed5e87083c1af9bc64978ac00fa5735
3
+ size 805863911
pytorch_model-00023-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ccf3e11b7d9a1d3c662ae5d85bf1d2502cc040ebaf0fff78db541a5caaebb1
3
+ size 805863911
pytorch_model-00024-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db45df5bcafe3f86da122a98f58519d1f1104ea8fcfac14dacec56cf5d8807e2
3
+ size 805863911
pytorch_model-00025-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5f469c82883caf20eb0f8531a1387caf129d76b5e0258312e5d952d32af08e
3
+ size 805863911
pytorch_model-00026-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a36de78bd83d474cc71aab1ac7ee66b19207020fcedc167acbab949802c86e8
3
+ size 805864103
pytorch_model-00027-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbf8f9fb75a5a24515940e12f300a8a2405a7f9cc206f4f6a8066b714de7904
3
+ size 805864103
pytorch_model-00028-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325e94d9fdbd43e7107f19a93b50a9b2b958752187801fdb165207e887a85e5c
3
+ size 805864103
pytorch_model-00029-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9694df632accdef5417efd96d35fb32114b177bbd87e3256c6420c9eeaa3dbb7
3
+ size 805864103
pytorch_model-00030-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf4acb18f9f1fcd53c504e4da1b8b69718cc85f3a9dce1f0e5f1ba2fb7dc2ea
3
+ size 805864103
pytorch_model-00031-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8f5919ebba7393fe5353d1630569b67498a19e9dcb972690986f214e8ea4f1
3
+ size 805864103
pytorch_model-00032-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1098ea66577e21fea402f9aae090ff0f326490b0c22abfed765ede75868d68a6
3
+ size 805864103
pytorch_model-00033-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32731f543f13bf822547b5443b51719805878fa74d52f49660872c18e871cafe
3
+ size 805864103
pytorch_model-00034-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ceb74ef8b5532cb61d2e1150f98dea2f992b6ded12508a357c93dca1ce6601
3
+ size 805864103
pytorch_model-00035-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef6be88e1845b0b4803eaea312d25d5ac6ff4766ba2f9e9acffc684a6fd1a87
3
+ size 805864103
pytorch_model-00036-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09352ca55737c00f25cd2d8da427623eb0eef698067eddc3b57b4a188f36988
3
+ size 805864103
pytorch_model-00037-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0f842d94fc4c4402e09a667cf695610256e52c1a2b4265feb105cb11b135f9
3
+ size 805864103
pytorch_model-00038-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d288b3b8d1499304c2b3e4f2d8354ac09a82dbf3e7ba249382861c6793c58c9
3
+ size 805864103
pytorch_model-00039-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f250184e62af5b10f8922ec3388533421d42afb214d723680a8c290cd2030913
3
+ size 805864103
pytorch_model-00040-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed0cc976baa2230c40dfe781482dd85e47a40c838cb9a041cab4775eb3ef4bd
3
+ size 805864103
pytorch_model-00041-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb4ae326ba957ea0ad5b4e5d809b020152c33ef131f401d0f7dd8f20514a240
3
+ size 805864103
pytorch_model-00042-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f061cc81342734309de48590c792bf4ee90261674eed607036c175916ac947
3
+ size 805864103
pytorch_model-00043-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d71406e68bca7f4709547747d1fb6957cc335efcca016afef113d0396778d20f
3
+ size 805864103
pytorch_model-00044-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89197e0a685965bed15b34e8765a3003086d759a8435b3f4d060c3313f9b44c
3
+ size 805864103
pytorch_model-00045-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c2a1c9b56560f98c5fc2eaff55f39221b7a582edf118af7e686a8b712c88d7
3
+ size 805864103
pytorch_model-00046-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2af36c9752848000d7470db4f1cf82573ba0645e64bb371b32c78c2b058866
3
+ size 805864103
pytorch_model-00047-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c6606321c5f684898c31fc1c08450574bca881affb76b7a03f44154937ac31
3
+ size 805864103
pytorch_model-00048-of-00129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b29aed8f540b71201283799a55c5a8dcfc38e21de101a1fc1ef1ddfec31e4f
3
+ size 805864103