Hugging Face's logo

alphadl
/
R1-Distill-1.5B-Qwen-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files Community
alphadl commited on
Commit
a17523e
·
verified ·
1 Parent(s): 447e170

Training in progress, step 12000

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.3",
25
- "use_cache": true,
26
  "use_sliding_window": false,
27
  "vocab_size": 151936
28
  }
 
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.3",
25
+ "use_cache": false,
26
  "use_sliding_window": false,
27
  "vocab_size": 151936
28
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9a9f711ba16782cee5802a8233d575b88158db97563349a666f35d2f33dece7
3
  size 3087467144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8b87238b90795f5352440fe7040981f2a7ed5d8271b2a54335a770d502004f
3
  size 3087467144
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be56b72f87a675bc42e8675128d3d059767b1ba323b1f6539aab8280abf7646d
3
  size 8440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6f25257ad45cc6baad1e36d43a3f0d37de49e29f34db11bd8ddd0885b7fe6c
3
  size 8440