Hugging Face's logo

yfliao
/
Qwen2.5-1.5B-Open-R1-Distill

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
yfliao commited on
Commit
0de349e
·
verified ·
1 Parent(s): 818ea72

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +3 -3
  2. model.safetensors +1 -1
  3. training_args.bin +2 -2
config.json CHANGED
@@ -19,11 +19,11 @@
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
  "rope_theta": 1000000.0,
22
- "sliding_window": null,
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.48.2",
26
- "use_cache": true,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
29
  }
 
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
  "rope_theta": 1000000.0,
22
+ "sliding_window": 32768,
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.49.0",
26
+ "use_cache": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
29
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d863cc4d7403185d92092c7532529acd49da9de2fa44ba2851caf3b46629a4d3
3
  size 3087467144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff006c9d1605c42ae8812a6b3c13f4c8740e56f356979195c8d74af10b4f88d6
3
  size 3087467144
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c87e93ad0b83c50b6f176b681c40c8ae2933f3d8bd16532f272daf32df2526b
3
- size 7416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb66e5d5092796a70b2f05176fa07b21203651f1287ac41c259f37e31c47d68
3
+ size 7544