Downloads · 30 days
6
14% of all-time downloads
qwen35-4b-phase2-dpo
hudsongouge/qwen35-4b-phase2-dpo
qwen35-4b-phase2-dpo is a machine learning model from hudsongouge. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
DPO on top of GRPO using evaluator PASS vs FAIL pairs from hudsongouge/podcast-transcripts-cleaned-phase2 (same-chunk preferences). Init: hudsongouge/qwen35-4b-grpo-rescue.
All-time downloads
43
Public
Repo size
700 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors680 MB · 97%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026
- SHA
- 0c3d9fcd
Base models
Model card
From the Hugging Face model README
qwen35-4b-phase2-dpo
DPO on top of GRPO using evaluator PASS vs FAIL pairs from
hudsongouge/podcast-transcripts-cleaned-phase2 (same-chunk preferences).
Init: hudsongouge/qwen35-4b-grpo-rescue.
- Library
- peft
- License
- apache-2.0
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026