shengyi-qian commited on
Commit
9c87696
·
1 Parent(s): 1a74a1a

three checkpoints

Browse files
Files changed (45) hide show
  1. qwen1.5_base_rule_base_arc_heavy_grpo_naive/added_tokens.json +3 -0
  2. qwen1.5_base_rule_base_arc_heavy_grpo_naive/config.json +3 -0
  3. qwen1.5_base_rule_base_arc_heavy_grpo_naive/generation_config.json +3 -0
  4. qwen1.5_base_rule_base_arc_heavy_grpo_naive/merges.txt +0 -0
  5. qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00001-of-00006.safetensors +3 -0
  6. qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00002-of-00006.safetensors +3 -0
  7. qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00003-of-00006.safetensors +3 -0
  8. qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00004-of-00006.safetensors +3 -0
  9. qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00005-of-00006.safetensors +3 -0
  10. qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00006-of-00006.safetensors +3 -0
  11. qwen1.5_base_rule_base_arc_heavy_grpo_naive/model.safetensors.index.json +3 -0
  12. qwen1.5_base_rule_base_arc_heavy_grpo_naive/special_tokens_map.json +3 -0
  13. qwen1.5_base_rule_base_arc_heavy_grpo_naive/tokenizer.json +3 -0
  14. qwen1.5_base_rule_base_arc_heavy_grpo_naive/tokenizer_config.json +3 -0
  15. qwen1.5_base_rule_base_arc_heavy_grpo_naive/vocab.json +3 -0
  16. qwen1.5_base_rule_base_equal_dist_grpo_naive/added_tokens.json +3 -0
  17. qwen1.5_base_rule_base_equal_dist_grpo_naive/config.json +3 -0
  18. qwen1.5_base_rule_base_equal_dist_grpo_naive/generation_config.json +3 -0
  19. qwen1.5_base_rule_base_equal_dist_grpo_naive/merges.txt +0 -0
  20. qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00001-of-00006.safetensors +3 -0
  21. qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00002-of-00006.safetensors +3 -0
  22. qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00003-of-00006.safetensors +3 -0
  23. qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00004-of-00006.safetensors +3 -0
  24. qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00005-of-00006.safetensors +3 -0
  25. qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00006-of-00006.safetensors +3 -0
  26. qwen1.5_base_rule_base_equal_dist_grpo_naive/model.safetensors.index.json +3 -0
  27. qwen1.5_base_rule_base_equal_dist_grpo_naive/special_tokens_map.json +3 -0
  28. qwen1.5_base_rule_base_equal_dist_grpo_naive/tokenizer.json +3 -0
  29. qwen1.5_base_rule_base_equal_dist_grpo_naive/tokenizer_config.json +3 -0
  30. qwen1.5_base_rule_base_equal_dist_grpo_naive/vocab.json +3 -0
  31. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/added_tokens.json +3 -0
  32. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/config.json +3 -0
  33. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/generation_config.json +3 -0
  34. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/merges.txt +0 -0
  35. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00001-of-00006.safetensors +3 -0
  36. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00002-of-00006.safetensors +3 -0
  37. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00003-of-00006.safetensors +3 -0
  38. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00004-of-00006.safetensors +3 -0
  39. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00005-of-00006.safetensors +3 -0
  40. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00006-of-00006.safetensors +3 -0
  41. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model.safetensors.index.json +3 -0
  42. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/special_tokens_map.json +3 -0
  43. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/tokenizer.json +3 -0
  44. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/tokenizer_config.json +3 -0
  45. qwen1.5_base_rule_base_imdb_heavy_grpo_naive/vocab.json +3 -0
qwen1.5_base_rule_base_arc_heavy_grpo_naive/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_grpo_naive/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_grpo_naive/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_grpo_naive/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398ed6b8910120c4a4456234523027a7b1f04c563cd55f5044ae34d12a343dca
3
+ size 4996577736
qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876097ab33daf5ffab6ee2dfb1a8f4e07ac721dbf57f81f2c00a7d0f0866d40b
3
+ size 4996347752
qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51cde50bc4d8ca824ff5a7f71bf21056d3dc6f1e924c7b79e97b6ea5bbd2499
3
+ size 4997127120
qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ec72aef63307f1f03f843aa0117328511f63254886adc74f95b5ed0fc4b56a
3
+ size 4985592520
qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3104478d1e3b81e144c21f970c73a43a266e8e1deb0542ede153ff5c6d2a1a
3
+ size 4996348976
qwen1.5_base_rule_base_arc_heavy_grpo_naive/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce399745c7d7519a68ffe31e59ab9b39a3289b2155eb3ddc59745e07a298923
3
+ size 3660151400
qwen1.5_base_rule_base_arc_heavy_grpo_naive/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_grpo_naive/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_grpo_naive/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_grpo_naive/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_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
qwen1.5_base_rule_base_equal_dist_grpo_naive/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_equal_dist_grpo_naive/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_equal_dist_grpo_naive/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_equal_dist_grpo_naive/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999e981ffc73b3c41d4d888f1a0d650f8a27800f9da9d059cd9271c4d508fc6c
3
+ size 4996577736
qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92052eb6de882d42fe91da94c51654c4a991d1b8b5affade829a04f063f640cb
3
+ size 4996347752
qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c71190b5687442d42fdff738868de61ca87c8f1d5fd870cab9bc795cb957fadd
3
+ size 4997127120
qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b0829cd121aa005e7b50f449e7a7fe8152d83bee737ab4d74c9bcf26e6080d
3
+ size 4985592520
qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39296277f9bc5ba4bc9d7a63d2ba835aa709b4f96bdf61ed13146bda85d6e8f1
3
+ size 4996348976
qwen1.5_base_rule_base_equal_dist_grpo_naive/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8df9278d78de617db0f80fac58ce781535583fbc8823bdb42e2104d7679fd91
3
+ size 3660151400
qwen1.5_base_rule_base_equal_dist_grpo_naive/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_equal_dist_grpo_naive/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_equal_dist_grpo_naive/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_equal_dist_grpo_naive/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_equal_dist_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
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/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_grpo_naive/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_grpo_naive/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_grpo_naive/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80461a2ca6e136782638c9322fed893ba5520f08fa245d38b3cfc841133fad47
3
+ size 4996577736
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c27b590e385e249425336f2c7a3b0883570abd4b67bdadb4fafd3ddc5945175
3
+ size 4996347752
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3548b5d2cca84242d3cbb321333c79b7e39f1d4f5dae8e02fa8bd3480fdc53
3
+ size 4997127120
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf1a97c7e85eeea45dac77f3ad7dc882f134b99ac703d14922cf3348999b0f17
3
+ size 4985592520
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93c81751690772b14473ad1d9ba9359e0cb5669ed324410ab8ea4368e6c7fbb
3
+ size 4996348976
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98dc18c927260bb6159404b697e9da7fb87710ce15aa4fc397bf6bb4994bbd75
3
+ size 3660151400
qwen1.5_base_rule_base_imdb_heavy_grpo_naive/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_grpo_naive/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_grpo_naive/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_grpo_naive/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_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