Hugging Face's logo

MoeReward
/
rl_checkpoints

Safetensors
Model card Files
xet
Community
shengyi-qian commited on
Commit
bfe5658
·
1 Parent(s): 09ddbb5

qwen2.5 final checkpoints

Browse files
Files changed (13) hide show
  1. qwen2.5_base_rule_base_imdb_main_grpo_naive/added_tokens.json +3 -0
  2. qwen2.5_base_rule_base_imdb_main_grpo_naive/config.json +3 -0
  3. qwen2.5_base_rule_base_imdb_main_grpo_naive/generation_config.json +3 -0
  4. qwen2.5_base_rule_base_imdb_main_grpo_naive/merges.txt +0 -0
  5. qwen2.5_base_rule_base_imdb_main_grpo_naive/model-00001-of-00004.safetensors +3 -0
  6. qwen2.5_base_rule_base_imdb_main_grpo_naive/model-00002-of-00004.safetensors +3 -0
  7. qwen2.5_base_rule_base_imdb_main_grpo_naive/model-00003-of-00004.safetensors +3 -0
  8. qwen2.5_base_rule_base_imdb_main_grpo_naive/model-00004-of-00004.safetensors +3 -0
  9. qwen2.5_base_rule_base_imdb_main_grpo_naive/model.safetensors.index.json +3 -0
  10. qwen2.5_base_rule_base_imdb_main_grpo_naive/special_tokens_map.json +3 -0
  11. qwen2.5_base_rule_base_imdb_main_grpo_naive/tokenizer.json +3 -0
  12. qwen2.5_base_rule_base_imdb_main_grpo_naive/tokenizer_config.json +3 -0
  13. qwen2.5_base_rule_base_imdb_main_grpo_naive/vocab.json +3 -0
qwen2.5_base_rule_base_imdb_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_imdb_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_imdb_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_imdb_main_grpo_naive/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5_base_rule_base_imdb_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:e0259829c65b7eb89c985f46484bd0d9025f576f72a5f8f5093f12c17e282525
3
+ size 4877660776
qwen2.5_base_rule_base_imdb_main_grpo_naive/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d74ceba4042015a032ea440bed3bf0f2efd45c3bb23429b29c25172e39235ac
3
+ size 4932751008
qwen2.5_base_rule_base_imdb_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:a9b0339de88efd7c50796ea776e1bc680ab429f65e848a64f09c07e5688ec1ce
3
+ size 4330865200
qwen2.5_base_rule_base_imdb_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:e7f17af94e22a05d2cdb64681342222708c11e685687774943ba98a98e2cc7bd
3
+ size 1089994880
qwen2.5_base_rule_base_imdb_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_imdb_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_imdb_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_imdb_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_imdb_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