Hugging Face's logo

Blancy
/
Qwen2.5-1.5B-Open-R1-GRPO

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
1
Blancy commited on
Commit
bc41eb0
·
verified ·
1 Parent(s): bc933a8

Training in progress, epoch 0

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
@@ -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 sha256:32847f455be8fe8a2590b02648a38842a8a118f1ef14da5b7f256a032fbf6b85
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6328843113ff8d5aa44f4845a1c5600e974857882c34842e470e657a29d2bb79
3
  size 3554214752
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c2e5d17dba8cffd9a6edadfe818c9ae65355b91e8e57ef7b3ccb994b5711b7e
3
  size 7928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0904404c7ae8f48f3e23df9f3b31c32ef32959420e406259d59b2d2d3953199c
3
  size 7928