Hugging Face's logo

MoeReward
/
rl_checkpoints

Safetensors
Model card Files Community
shengyi-qian commited on
Commit
09ddbb5
·
1 Parent(s): 2581e08

upload qwen2.5 7 checkpoints

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. qwen2.5_base_rule_base_arc_main_disco/added_tokens.json +3 -0
  2. qwen2.5_base_rule_base_arc_main_disco/config.json +3 -0
  3. qwen2.5_base_rule_base_arc_main_disco/generation_config.json +3 -0
  4. qwen2.5_base_rule_base_arc_main_disco/merges.txt +0 -0
  5. qwen2.5_base_rule_base_arc_main_disco/model-00001-of-00004.safetensors +3 -0
  6. qwen2.5_base_rule_base_arc_main_disco/model-00002-of-00004.safetensors +3 -0
  7. qwen2.5_base_rule_base_arc_main_disco/model-00003-of-00004.safetensors +3 -0
  8. qwen2.5_base_rule_base_arc_main_disco/model-00004-of-00004.safetensors +3 -0
  9. qwen2.5_base_rule_base_arc_main_disco/model.safetensors.index.json +3 -0
  10. qwen2.5_base_rule_base_arc_main_disco/special_tokens_map.json +3 -0
  11. qwen2.5_base_rule_base_arc_main_disco/tokenizer.json +3 -0
  12. qwen2.5_base_rule_base_arc_main_disco/tokenizer_config.json +3 -0
  13. qwen2.5_base_rule_base_arc_main_disco/vocab.json +3 -0
  14. qwen2.5_base_rule_base_arc_main_grpo_naive/added_tokens.json +3 -0
  15. qwen2.5_base_rule_base_arc_main_grpo_naive/config.json +3 -0
  16. qwen2.5_base_rule_base_arc_main_grpo_naive/generation_config.json +3 -0
  17. qwen2.5_base_rule_base_arc_main_grpo_naive/merges.txt +0 -0
  18. qwen2.5_base_rule_base_arc_main_grpo_naive/model-00001-of-00004.safetensors +3 -0
  19. qwen2.5_base_rule_base_arc_main_grpo_naive/model-00002-of-00004.safetensors +3 -0
  20. qwen2.5_base_rule_base_arc_main_grpo_naive/model-00003-of-00004.safetensors +3 -0
  21. qwen2.5_base_rule_base_arc_main_grpo_naive/model-00004-of-00004.safetensors +3 -0
  22. qwen2.5_base_rule_base_arc_main_grpo_naive/model.safetensors.index.json +3 -0
  23. qwen2.5_base_rule_base_arc_main_grpo_naive/special_tokens_map.json +3 -0
  24. qwen2.5_base_rule_base_arc_main_grpo_naive/tokenizer.json +3 -0
  25. qwen2.5_base_rule_base_arc_main_grpo_naive/tokenizer_config.json +3 -0
  26. qwen2.5_base_rule_base_arc_main_grpo_naive/vocab.json +3 -0
  27. qwen2.5_base_rule_base_imdb_main_disco/added_tokens.json +3 -0
  28. qwen2.5_base_rule_base_imdb_main_disco/config.json +3 -0
  29. qwen2.5_base_rule_base_imdb_main_disco/generation_config.json +3 -0
  30. qwen2.5_base_rule_base_imdb_main_disco/merges.txt +0 -0
  31. qwen2.5_base_rule_base_imdb_main_disco/model-00001-of-00004.safetensors +3 -0
  32. qwen2.5_base_rule_base_imdb_main_disco/model-00002-of-00004.safetensors +3 -0
  33. qwen2.5_base_rule_base_imdb_main_disco/model-00003-of-00004.safetensors +3 -0
  34. qwen2.5_base_rule_base_imdb_main_disco/model-00004-of-00004.safetensors +3 -0
  35. qwen2.5_base_rule_base_imdb_main_disco/model.safetensors.index.json +3 -0
  36. qwen2.5_base_rule_base_imdb_main_disco/special_tokens_map.json +3 -0
  37. qwen2.5_base_rule_base_imdb_main_disco/tokenizer.json +3 -0
  38. qwen2.5_base_rule_base_imdb_main_disco/tokenizer_config.json +3 -0
  39. qwen2.5_base_rule_base_imdb_main_disco/vocab.json +3 -0
  40. qwen2.5_base_rule_base_math_main_disco/added_tokens.json +3 -0
  41. qwen2.5_base_rule_base_math_main_disco/config.json +3 -0
  42. qwen2.5_base_rule_base_math_main_disco/generation_config.json +3 -0
  43. qwen2.5_base_rule_base_math_main_disco/merges.txt +0 -0
  44. qwen2.5_base_rule_base_math_main_disco/model-00001-of-00004.safetensors +3 -0
  45. qwen2.5_base_rule_base_math_main_disco/model-00002-of-00004.safetensors +3 -0
  46. qwen2.5_base_rule_base_math_main_disco/model-00003-of-00004.safetensors +3 -0
  47. qwen2.5_base_rule_base_math_main_disco/model-00004-of-00004.safetensors +3 -0
  48. qwen2.5_base_rule_base_math_main_disco/model.safetensors.index.json +3 -0
  49. qwen2.5_base_rule_base_math_main_disco/special_tokens_map.json +3 -0
  50. qwen2.5_base_rule_base_math_main_disco/tokenizer.json +3 -0
qwen2.5_base_rule_base_arc_main_disco/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
qwen2.5_base_rule_base_arc_main_disco/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e01b109edab58e2487ea9a47d60c79f3680fa07f10a04e65b67cc17bc39568
3
+ size 747
qwen2.5_base_rule_base_arc_main_disco/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd5fc7bcb9d08b94f281fdc05a5fcbcafa1acce7c26270c2350129444462e17c
3
+ size 117
qwen2.5_base_rule_base_arc_main_disco/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5_base_rule_base_arc_main_disco/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86091d36ae438ad1e88e8e6322da45805fb3348f77fd476ffb8a7d80686564f0
3
+ size 4877660776
qwen2.5_base_rule_base_arc_main_disco/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779f1b628e08d9ba9b9b5d0eef075a23ee9a42b3d85ff2886d65d5743e1ed7f2
3
+ size 4932751008
qwen2.5_base_rule_base_arc_main_disco/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ddb45acdcd3deac6d8d855c084596672841f3696b95ee9bc6f00a0867f92d18
3
+ size 4330865200
qwen2.5_base_rule_base_arc_main_disco/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbef1967c0f573e823d9b732e028658252b1de83322ba1bd189e1fe659e583f7
3
+ size 1089994880
qwen2.5_base_rule_base_arc_main_disco/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb
3
+ size 27752
qwen2.5_base_rule_base_arc_main_disco/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
3
+ size 616
qwen2.5_base_rule_base_arc_main_disco/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
3
+ size 11421995
qwen2.5_base_rule_base_arc_main_disco/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dae0102f342a3b6bc2a4d03f430ed83666dcab8879c9ee44c08a3d9095132d
3
+ size 7259
qwen2.5_base_rule_base_arc_main_disco/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833
qwen2.5_base_rule_base_arc_main_grpo_naive/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
qwen2.5_base_rule_base_arc_main_grpo_naive/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e01b109edab58e2487ea9a47d60c79f3680fa07f10a04e65b67cc17bc39568
3
+ size 747
qwen2.5_base_rule_base_arc_main_grpo_naive/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd5fc7bcb9d08b94f281fdc05a5fcbcafa1acce7c26270c2350129444462e17c
3
+ size 117
qwen2.5_base_rule_base_arc_main_grpo_naive/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5_base_rule_base_arc_main_grpo_naive/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650334e5e5400dfc5ff9bdc197985331139541fb485eea1f45bc6fc22e6789dd
3
+ size 4877660776
qwen2.5_base_rule_base_arc_main_grpo_naive/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e44572a4717d80a022ec39f8b00f4e0c69a63eea835e2f9d74f01d00f75b23e
3
+ size 4932751008
qwen2.5_base_rule_base_arc_main_grpo_naive/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f301a9cb97371278ec723a7a4783d6de423a2838c2d6ca86d0d1ccdb3969b6
3
+ size 4330865200
qwen2.5_base_rule_base_arc_main_grpo_naive/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343bcfbb609b144159f3a75866b6641c683b17550f465b7e6b12ba8fe4fa29c7
3
+ size 1089994880
qwen2.5_base_rule_base_arc_main_grpo_naive/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb
3
+ size 27752
qwen2.5_base_rule_base_arc_main_grpo_naive/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
3
+ size 616
qwen2.5_base_rule_base_arc_main_grpo_naive/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
3
+ size 11421995
qwen2.5_base_rule_base_arc_main_grpo_naive/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dae0102f342a3b6bc2a4d03f430ed83666dcab8879c9ee44c08a3d9095132d
3
+ size 7259
qwen2.5_base_rule_base_arc_main_grpo_naive/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833
qwen2.5_base_rule_base_imdb_main_disco/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
qwen2.5_base_rule_base_imdb_main_disco/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e01b109edab58e2487ea9a47d60c79f3680fa07f10a04e65b67cc17bc39568
3
+ size 747
qwen2.5_base_rule_base_imdb_main_disco/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd5fc7bcb9d08b94f281fdc05a5fcbcafa1acce7c26270c2350129444462e17c
3
+ size 117
qwen2.5_base_rule_base_imdb_main_disco/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5_base_rule_base_imdb_main_disco/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f988b8ebf4dc4fbd81fe2da3792c2a541658d31143bc2c06c7ed8c944fe937
3
+ size 4877660776
qwen2.5_base_rule_base_imdb_main_disco/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7be06780b7723247deee092d0d87293626c7c44a7572c549bee7766112d76a
3
+ size 4932751008
qwen2.5_base_rule_base_imdb_main_disco/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fc6052e586f8c99bd823ab0d90adba794e68de97ffb073b832d72670db1417
3
+ size 4330865200
qwen2.5_base_rule_base_imdb_main_disco/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803424724eb0d73af76c84b82af8f45081a9f478a0697a224cba5484d9213b20
3
+ size 1089994880
qwen2.5_base_rule_base_imdb_main_disco/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb
3
+ size 27752
qwen2.5_base_rule_base_imdb_main_disco/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
3
+ size 616
qwen2.5_base_rule_base_imdb_main_disco/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
3
+ size 11421995
qwen2.5_base_rule_base_imdb_main_disco/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dae0102f342a3b6bc2a4d03f430ed83666dcab8879c9ee44c08a3d9095132d
3
+ size 7259
qwen2.5_base_rule_base_imdb_main_disco/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833
qwen2.5_base_rule_base_math_main_disco/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
qwen2.5_base_rule_base_math_main_disco/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e01b109edab58e2487ea9a47d60c79f3680fa07f10a04e65b67cc17bc39568
3
+ size 747
qwen2.5_base_rule_base_math_main_disco/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd5fc7bcb9d08b94f281fdc05a5fcbcafa1acce7c26270c2350129444462e17c
3
+ size 117
qwen2.5_base_rule_base_math_main_disco/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5_base_rule_base_math_main_disco/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ca178804be9827922ac22d5adc00e3e0ff2678ad65028ae9b945dad783d3d5
3
+ size 4877660776
qwen2.5_base_rule_base_math_main_disco/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5017fb7a5576ee0acbc9cb65f617df1b8a530ebf0b99592d8863c6744bd8d6d9
3
+ size 4932751008
qwen2.5_base_rule_base_math_main_disco/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e36f97de7cb1841848ba4762550bd05e8100f23a11e575fdbf63c7e22fa621a
3
+ size 4330865200
qwen2.5_base_rule_base_math_main_disco/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349ec227bc86d9ee1879d839e1ec3abe09e74b4d5a8c7ed946b517fbd8ef05a1
3
+ size 1089994880
qwen2.5_base_rule_base_math_main_disco/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb
3
+ size 27752
qwen2.5_base_rule_base_math_main_disco/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
3
+ size 616
qwen2.5_base_rule_base_math_main_disco/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
3
+ size 11421995