Hugging Face's logo

MoeReward
/
rl_checkpoints

Safetensors
Model card Files Community
shengyi-qian commited on
Commit
1a74a1a
·
1 Parent(s): b90be05

qwen1.5 rule based

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. qwen1.5_base_rule_base_grpo_naive/added_tokens.json +3 -0
  3. qwen1.5_base_rule_base_grpo_naive/config.json +3 -0
  4. qwen1.5_base_rule_base_grpo_naive/generation_config.json +3 -0
  5. qwen1.5_base_rule_base_grpo_naive/merges.txt +0 -0
  6. qwen1.5_base_rule_base_grpo_naive/model-00001-of-00006.safetensors +3 -0
  7. qwen1.5_base_rule_base_grpo_naive/model-00002-of-00006.safetensors +3 -0
  8. qwen1.5_base_rule_base_grpo_naive/model-00003-of-00006.safetensors +3 -0
  9. qwen1.5_base_rule_base_grpo_naive/model-00004-of-00006.safetensors +3 -0
  10. qwen1.5_base_rule_base_grpo_naive/model-00005-of-00006.safetensors +3 -0
  11. qwen1.5_base_rule_base_grpo_naive/model-00006-of-00006.safetensors +3 -0
  12. qwen1.5_base_rule_base_grpo_naive/model.safetensors.index.json +3 -0
  13. qwen1.5_base_rule_base_grpo_naive/special_tokens_map.json +3 -0
  14. qwen1.5_base_rule_base_grpo_naive/tokenizer.json +3 -0
  15. qwen1.5_base_rule_base_grpo_naive/tokenizer_config.json +3 -0
  16. qwen1.5_base_rule_base_grpo_naive/vocab.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.json filter=lfs diff=lfs merge=lfs -text
qwen1.5_base_rule_base_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_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_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_grpo_naive/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_grpo_naive/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b68e7c9fb695ce2542cb0b4e9aa39b4a73f52c390c91d9e4064dec3d38c285
3
+ size 4996577736
qwen1.5_base_rule_base_grpo_naive/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30bd9275dba7c546a17f399e6eadd8bd7277667ce56bb0e4a804259d77e8f561
3
+ size 4996347752
qwen1.5_base_rule_base_grpo_naive/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce23d4b423fa414696e35aa0851b36d4ca0c55b8f421dc2345fd69a24ec0547
3
+ size 4997127120
qwen1.5_base_rule_base_grpo_naive/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6efec54b727416d08be2536f7d3e331c0cdd455d1eab3f530ce10bc4c69c9d7
3
+ size 4985592520
qwen1.5_base_rule_base_grpo_naive/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7405e1c66c1a81d9c87cd03de97d0c0b02c966831a6b723bca0f58154a753d48
3
+ size 4996348976
qwen1.5_base_rule_base_grpo_naive/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22694f56a2fe188eff6dbb990655fae3517ec6cc036bf11a1c8a7fe8e6c0d62
3
+ size 3660151400
qwen1.5_base_rule_base_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_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_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_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_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