Hugging Face's logo

js2025
/
Qwen2.5-0.5B-Open-R1-Code-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
js2025 commited on
Commit
68396ea
·
verified ·
1 Parent(s): 8b36b35

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. tokenizer.json +2 -2
  4. training_args.bin +1 -1
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "tie_word_embeddings": true,
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": 151936
 
23
  "tie_word_embeddings": true,
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": 151936
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d60938287d8bfb4f9cd69426078d8cfb3a705a8ba29b51347207d5ec7d03a82
3
  size 1260367448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1066f84478b69b09f285a26368453cdab36a4eef626a1762dda1991780494d
3
  size 1260367448
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 sha256:62d4b6b5573eecf72a2bf9b39f1c8b3b1bd8293aaf565853cd0f096a058b56b6
3
  size 10296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a5a879f311d540a91a091650fd35292d8927b4bfd9ab5967ddbd2d588b7ba3d
3
  size 10296