Hugging Face's logo

Blancy
/
Qwen-2.5-7B-Simple-RL

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Blancy commited on
Commit
2d6ba23
·
verified ·
1 Parent(s): c24ae74

Training in progress, step 7

Browse files
Files changed (7) hide show
  1. config.json +1 -1
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. tokenizer.json +2 -2
  7. training_args.bin +1 -1
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0",
26
- "use_cache": true,
27
  "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 152064
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0",
26
+ "use_cache": false,
27
  "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 152064
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ac23a088a144b682329091bc05c9420822823dfd4779e5e225c833c7d6d5217
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f41b91b45e80cffa55fa801fea72211e9148c19d03125b838de48848ebbda45
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03c306d3f6e953ea1b8e4cdbce21ed723ecebeaf8033a49359becb5f64c2ffb2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75f1cb375d6fecb6f5ac5c1b513d4ff76b5bed28603fcfbffc86343cef99f121
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbb0d2cdd9f0d33072a4c3e8dda09f16ff3dd9150c44353f94c33a71e4682f61
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7da8c5e578630a0a69104e3f025bb14a7eeec3d91d2bc244981dc680073d02
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c3fd103ad1f1fc0958920d288e339655f00501544a7cb019c638440edad3148
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cf8ee14bfd36f3d1171f3233835fb278a5a372a805c21284bb8eda64a6c219
3
  size 1089994880
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16cc1b1e48257d39d2951ed925aa698e51ce18cd8c8d494b42c420bebbe751fe
3
  size 7864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:852b2dd947c2e9f24a0aa57be39d07a5b97e054057f10119e54131d893efbd68
3
  size 7864