Hugging Face's logo

MoeReward
/
rl_checkpoints

Safetensors
Model card Files Community
shengyi-qian commited on
Commit
54cb21f
·
1 Parent(s): 3a91c0a

upload diffdomain1

Browse files
Files changed (45) hide show
  1. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/added_tokens.json +3 -0
  2. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/config.json +3 -0
  3. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/generation_config.json +3 -0
  4. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/merges.txt +0 -0
  5. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors +3 -0
  6. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors +3 -0
  7. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors +3 -0
  8. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors +3 -0
  9. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors +3 -0
  10. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors +3 -0
  11. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model.safetensors.index.json +3 -0
  12. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/special_tokens_map.json +3 -0
  13. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/tokenizer.json +3 -0
  14. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/tokenizer_config.json +3 -0
  15. qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/vocab.json +3 -0
  16. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/added_tokens.json +3 -0
  17. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/config.json +3 -0
  18. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/generation_config.json +3 -0
  19. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/merges.txt +0 -0
  20. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors +3 -0
  21. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors +3 -0
  22. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors +3 -0
  23. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors +3 -0
  24. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors +3 -0
  25. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors +3 -0
  26. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model.safetensors.index.json +3 -0
  27. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/special_tokens_map.json +3 -0
  28. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/tokenizer.json +3 -0
  29. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/tokenizer_config.json +3 -0
  30. qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/vocab.json +3 -0
  31. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/added_tokens.json +3 -0
  32. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/config.json +3 -0
  33. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/generation_config.json +3 -0
  34. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/merges.txt +0 -0
  35. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors +3 -0
  36. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors +3 -0
  37. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors +3 -0
  38. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors +3 -0
  39. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors +3 -0
  40. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors +3 -0
  41. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model.safetensors.index.json +3 -0
  42. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/special_tokens_map.json +3 -0
  43. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/tokenizer.json +3 -0
  44. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/tokenizer_config.json +3 -0
  45. qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/vocab.json +3 -0
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a475432c61f8d6154d10d28c37671a36e5717daf3d15002a988968fee54a500
3
+ size 80
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528d3faa3d28fe193cae05b08cd0c15e6c173fe3ed86ca4382d22ad120232280
3
+ size 1008
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64249e16a9efa9b4b2560bd2c0b3c44dd0eee067c5792b646bafe09f4676bce8
3
+ size 139
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7796490e49e00a8b97891356e6e26a4cd13265dd17b56a92b25df332c6067bd
3
+ size 4996577736
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5180207ba01db18c636333ec0e2190345f770ba528c77b4f2ec32bb5def407a
3
+ size 4996347752
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea444a0506c7be2952fe38dbf3bd3cdad2829e32943a74d1c23ef0e910b38cc
3
+ size 4997127120
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776be726b1b44bfaae14a41b3050cbc6d12d365f3044eafda1276609608a857d
3
+ size 4985592520
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4091a0eb2b25bb81765577c2d1d24db8f042d7a75a2651f5b5725a4cdad978
3
+ size 4996348976
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740d0506d961fdca78d749bf385695172125b5b49d9844469b6f6a5375896957
3
+ size 3660151400
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406d3a66074ba34fa2be1c70f976607e4eab4c192dbba1d9f066db2cf6531a42
3
+ size 416452
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf48284de8f4779b1dbf20963a68180002fba2a34a5da72292380c5d9fb6af2
3
+ size 370
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49bebc2336dd0896ee055aa24e6bb65d80539b16751bb9798d6829db3ac4ea3
3
+ size 11418365
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb94faf6d8d2be1485bba6ceb83a7f0c6885357867f2f662e6f3a6783b927c4
3
+ size 1331
qwen1.5_base_rule_base_arc_heavy_diffdomain1_reward_func/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a475432c61f8d6154d10d28c37671a36e5717daf3d15002a988968fee54a500
3
+ size 80
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528d3faa3d28fe193cae05b08cd0c15e6c173fe3ed86ca4382d22ad120232280
3
+ size 1008
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64249e16a9efa9b4b2560bd2c0b3c44dd0eee067c5792b646bafe09f4676bce8
3
+ size 139
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b62995b51d05b653c5ba7c794741ec75dac92c12445a686eb6cd98e0c505e7
3
+ size 4996577736
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad75f3ac05ae41d645da1acbb450e82cf8f72fbde9c2f654f3ba23faaffb1bc
3
+ size 4996347752
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daafbdcbf4c9903ff52eb9e1c03465d0150ddd9f8df5c835be7e48d967673f5e
3
+ size 4997127120
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f5017a8ae41d6e934e1ae8bced84448b2d8831febc4276e2c8ed0d10246382
3
+ size 4985592520
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c86c42837700498f4b88defcca7835d58d1e969bba390fbe1fa0179551def83
3
+ size 4996348976
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2e4244ae50a44a6c5efe7b826ee978890f14a92794175800fb3a5f5af72767
3
+ size 3660151400
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406d3a66074ba34fa2be1c70f976607e4eab4c192dbba1d9f066db2cf6531a42
3
+ size 416452
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf48284de8f4779b1dbf20963a68180002fba2a34a5da72292380c5d9fb6af2
3
+ size 370
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49bebc2336dd0896ee055aa24e6bb65d80539b16751bb9798d6829db3ac4ea3
3
+ size 11418365
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb94faf6d8d2be1485bba6ceb83a7f0c6885357867f2f662e6f3a6783b927c4
3
+ size 1331
qwen1.5_base_rule_base_imdb_heavy_diffdomain1_reward_func/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a475432c61f8d6154d10d28c37671a36e5717daf3d15002a988968fee54a500
3
+ size 80
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528d3faa3d28fe193cae05b08cd0c15e6c173fe3ed86ca4382d22ad120232280
3
+ size 1008
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64249e16a9efa9b4b2560bd2c0b3c44dd0eee067c5792b646bafe09f4676bce8
3
+ size 139
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d6add9c0e2d392622785b8faa5a4881d8284ba471312d6bf4832af0bbd5257f
3
+ size 4996577736
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e4ee1e79f57dd4e9dd708396412d1732fcaa50ea114d533839559bb57e6ba56
3
+ size 4996347752
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40d2d563e8b77d8ecf47baf61eafe0f9df50a32462f3d64c5c9db20b92cda18f
3
+ size 4997127120
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5c9b63e224f47324fd2dd11c889c66e3f79751dc569a9884584e761e87891a
3
+ size 4985592520
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdfe3675c726a815b65a61918e2bd0e958b631d0e1e6c4ab86675c9624b303c
3
+ size 4996348976
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377643658b38929fb96f412c0fa4893ceade3824cdb9d8ca2c03e53bbebeff90
3
+ size 3660151400
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406d3a66074ba34fa2be1c70f976607e4eab4c192dbba1d9f066db2cf6531a42
3
+ size 416452
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf48284de8f4779b1dbf20963a68180002fba2a34a5da72292380c5d9fb6af2
3
+ size 370
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49bebc2336dd0896ee055aa24e6bb65d80539b16751bb9798d6829db3ac4ea3
3
+ size 11418365
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb94faf6d8d2be1485bba6ceb83a7f0c6885357867f2f662e6f3a6783b927c4
3
+ size 1331
qwen1.5_base_rule_base_math_heavy_diffdomain1_reward_func/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833