Hugging Face's logo

yuyijiong
/
Qwen3-SWA-adaptation

Text Generation
Transformers
Safetensors
English
Chinese
Model card Files
xet
Community
1
yuyijiong commited on
Commit
c68b566
·
verified ·
1 Parent(s): ec2daa8

Add files using upload-large-folder tool

Browse files
Files changed (38) hide show
  1. .gitattributes +6 -0
  2. Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-870/adapter_model.safetensors +3 -0
  3. Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-870/training_args.bin +3 -0
  4. Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec/checkpoint-994/training_args.bin +3 -0
  5. Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=100_fadec/checkpoint-870/training_args.bin +3 -0
  6. Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0/checkpoint-862/adapter_model.safetensors +3 -0
  7. Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0/checkpoint-862/training_args.bin +3 -0
  8. Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2/checkpoint-862/adapter_model.safetensors +3 -0
  9. Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2/checkpoint-862/training_args.bin +3 -0
  10. Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-862/adapter_model.safetensors +3 -0
  11. Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-862/tokenizer.json +3 -0
  12. Qwen3-30B-A3B-Thinking-2507-sft-fusang/checkpoint-862/adapter_model.safetensors +3 -0
  13. Qwen3-30B-A3B-Thinking-2507-sft-fusang/checkpoint-862/tokenizer.json +3 -0
  14. Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-1302/adapter_model.safetensors +3 -0
  15. Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-1736/adapter_model.safetensors +3 -0
  16. Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-1736/training_args.bin +3 -0
  17. Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-1760/adapter_model.safetensors +3 -0
  18. Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-1760/training_args.bin +3 -0
  19. Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=100/checkpoint-1760/training_args.bin +3 -0
  20. Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=100_falayer=25_from1_step2_fadec/checkpoint-921/adapter_model.safetensors +3 -0
  21. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0/checkpoint-876/adapter_model.safetensors +3 -0
  22. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-2778/tokenizer.json +3 -0
  23. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-2778/training_args.bin +3 -0
  24. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=13_from0_step4_fadec/checkpoint-1771/adapter_model.safetensors +3 -0
  25. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec/checkpoint-1771/adapter_model.safetensors +3 -0
  26. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2/checkpoint-1771/adapter_model.safetensors +3 -0
  27. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2/checkpoint-1771/tokenizer.json +3 -0
  28. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2_fadec/checkpoint-1771/adapter_model.safetensors +3 -0
  29. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=10/checkpoint-1664/adapter_model.safetensors +3 -0
  30. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=10/checkpoint-1664/tokenizer.json +3 -0
  31. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1059/adapter_model.safetensors +3 -0
  32. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1059/tokenizer.json +3 -0
  33. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1059/training_args.bin +3 -0
  34. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1771/adapter_model.safetensors +3 -0
  35. Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100_falayer=25_from1_step2_fadec/checkpoint-926/adapter_model.safetensors +3 -0
  36. Qwen3-4B-Thinking-2507-sft-fusang-swa=4k_sink=0_fadec/checkpoint-1771/adapter_model.safetensors +3 -0
  37. Qwen3-4B-Thinking-2507-sft-fusang-swa=4k_sink=0_fadec/checkpoint-1771/training_args.bin +3 -0
  38. Qwen3-4B-Thinking-2507-sft-fusang/checkpoint-1771/training_args.bin +3 -0
.gitattributes CHANGED
@@ -47,3 +47,9 @@ Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=100_fadec/checkpoint-870/toke
47
  Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec/checkpoint-994/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
  Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=10/checkpoint-1760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
  Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-1760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
47
  Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec/checkpoint-994/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
  Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=10/checkpoint-1760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
  Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-1760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-2778/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=10/checkpoint-1664/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
+ Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-862/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
+ Qwen3-30B-A3B-Thinking-2507-sft-fusang/checkpoint-862/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2/checkpoint-1771/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
+ Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1059/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-870/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689a95b331b774125a4c9d4caf56df5904b311069cd59d8f8b950464fd844697
3
+ size 34641592
Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-870/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c0c733e79f44126ded37d6807317fff89067232da167d5cd9d0ff5c1e33f8c
3
+ size 5905
Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec/checkpoint-994/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e8903bdb8d86d0e0a423fb27f44ae98e694f59abb03a783fa347be186e0ccd
3
+ size 5969
Qwen3-30B-A3B-Instruct-2507-sft-fusang-swa=2k_sink=100_fadec/checkpoint-870/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712f6b102a08c50cb84eed63b859ecf745da435c0b6923c595d71503a218618d
3
+ size 5969
Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0/checkpoint-862/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149393deed25cb77d9209fab9277f1af1ad963a49a62082a48c6665c2e7ad9e9
3
+ size 34641592
Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0/checkpoint-862/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5d48fa8b00ec8464aa8f6f8b3cfefa02600c875d3c745dd0fbb2f2b0992a9c
3
+ size 5905
Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2/checkpoint-862/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f766e98a865feb4d479044e91b346f52c34125c78de5ccb531c44e657874b66
3
+ size 34641592
Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2/checkpoint-862/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6160b133ec995b406cb42ef9026aee458104d2b919ba53963d7c74c6f87e16
3
+ size 5969
Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-862/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd51dc999b9114869df18e0d1306831d6bd58da5a8e76117c49395d76f12bec
3
+ size 34641592
Qwen3-30B-A3B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-862/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
Qwen3-30B-A3B-Thinking-2507-sft-fusang/checkpoint-862/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b150564c2c838ca05e076fd565f850e31605493659fe4693c9989b6d1063feb4
3
+ size 34641592
Qwen3-30B-A3B-Thinking-2507-sft-fusang/checkpoint-862/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-1302/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8788613cc981016f4027fa928fe5548817a444b4bad0c350ffff8c75324c1e4
3
+ size 31879488
Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-1736/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39338841b072812ef91b9f37e8b1f7496ad4f872f4f293aa85a079ce752f728b
3
+ size 31879488
Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0/checkpoint-1736/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a74cd4e545b26b8d76bfdb341d64d8856f079f51238d6894f79fe4723b7c9e3
3
+ size 5841
Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-1760/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f673a59307132a988daae987b53ada768037e5deed81d2f2cc39b61eabe3f4
3
+ size 31879488
Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-1760/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d716b8b9cfebd952db4d1830c7f14ad512364499b81a5353abeb30696b2f0b6f
3
+ size 5841
Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=100/checkpoint-1760/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd71d523608647b510c6177d9725904b32d3b370830a08ab56fa0c02e0c2817
3
+ size 5905
Qwen3-4B-Instruct-2507-sft-fusang-swa=2k_sink=100_falayer=25_from1_step2_fadec/checkpoint-921/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcaa580a6f44a0a17504a4740a59f9ff81880124ad421357d1dd8e38098ca6ee
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0/checkpoint-876/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9669f5c4f3fbc99d585c82fc4e2a14d59cbc0be7e8d92c138c84502bc53f7363
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-2778/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_fadec/checkpoint-2778/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5fe068f7860db0f7a3c4ce9f694398c48e2f8f7584459d96c38c7af0ff60da
3
+ size 5905
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=13_from0_step4_fadec/checkpoint-1771/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8021e2e32839172ca3820feccf1fefdba103ddad810ed0bc37da1d7ed0bf33
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from0_step2_fadec/checkpoint-1771/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495089c0dd09c1c53899ef80b366986eda13d089fca5ff40fb1cadaf6769cca8
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2/checkpoint-1771/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de41efe0e9da4174ab331a60801b93fb534e92c2540dbc3d7851bff43fbd2c0
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2/checkpoint-1771/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=0_falayer=25_from1_step2_fadec/checkpoint-1771/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b940626a05d0f3b2280d7a85fcf14130a50110a8c5c5ddadfb2215450482b6
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=10/checkpoint-1664/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa8eb43259a053a2cf3a82c3d96cf1a6fdb5d4f75a18f1cfc95d3a8424dc1d0
3
+ size 47224624
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=10/checkpoint-1664/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1059/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ad162f7d877bc4051bb9e07bd2bdd80a674772c612e3c6e1f70ddc8c6f3d12
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1059/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1059/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e5de913c7d8e4235822896d33ed5aa00e8290bca0f6255497e982050f946d2
3
+ size 5905
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100/checkpoint-1771/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:501c5121b65ef138532c489a233847388e2c9d0e63195488fe114e35c8fa25fd
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=2k_sink=100_falayer=25_from1_step2_fadec/checkpoint-926/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04da1309f2dd2ed43d104541269615dab64d14861f335802553b7488b9586ca
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=4k_sink=0_fadec/checkpoint-1771/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea4911ab6943ff7c5e74c7e323c7ac52c6654c547c705ab35e6f39a74542238
3
+ size 31879488
Qwen3-4B-Thinking-2507-sft-fusang-swa=4k_sink=0_fadec/checkpoint-1771/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ebc1749d22860d6bbfa6867dfa8da495c9cfdf60fb5bb75e7df464c7219f487
3
+ size 5841
Qwen3-4B-Thinking-2507-sft-fusang/checkpoint-1771/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d1f3cce2f26b60214aa919feee1524a354472b5b8331be549ae1372e2ca2bf
3
+ size 5841