Hugging Face's logo

matthewchung74
/
Qwen2.5_3B-GRPO-medical-reasoning

Text Generation
Transformers
Safetensors
qwen2
unsloth
trl
grpo
medical-reasoning
qwen
conversational
text-generation-inference
Model card Files Community
matthewchung74 commited on
Commit
4e0e490
·
verified ·
1 Parent(s): 7e742e6

Trained with Unsloth

Browse files
Files changed (4) hide show
  1. config.json +2 -2
  2. generation_config.json +1 -1
  3. model-00001-of-00002.safetensors +1 -1
  4. model-00002-of-00002.safetensors +1 -1
config.json CHANGED
@@ -22,9 +22,9 @@
22
  "sliding_window": null,
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.48.3",
26
  "unsloth_fixed": true,
27
- "unsloth_version": "2025.2.9",
28
  "use_cache": true,
29
  "use_sliding_window": false,
30
  "vocab_size": 151936
 
22
  "sliding_window": null,
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.49.0",
26
  "unsloth_fixed": true,
27
+ "unsloth_version": "2025.2.4",
28
  "use_cache": true,
29
  "use_sliding_window": false,
30
  "vocab_size": 151936
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "eos_token_id": 151645,
4
  "max_length": 32768,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.48.3"
7
  }
 
3
  "eos_token_id": 151645,
4
  "max_length": 32768,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.49.0"
7
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cab48e0d591233e219cb7ac72851e9baf379dbac2ca65a4817c48fa02c801ba
3
  size 4957560304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635302a3510ddd9457ed79ecd791a5e54317cde6b709fe689bc863ed15122d20
3
  size 4957560304
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f58c4e130732a1c59ec21e8447506954bb2e2688410ed5ccc88a0cc8247f6d0e
3
  size 1214366696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99d75b2d1b226d338f729402eda9a2bbbff8c22eb97e3e8ae78830722ccc965
3
  size 1214366696