Downloads · 30 days
17
28% of all-time downloads
hudsongouge/qwen35-4b-nvfp4-podcast-cleaner-grpo
qwen35-4b-nvfp4-podcast-cleaner-grpo is a image-text-to-text model from hudsongouge. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Merged NVFP4 (llm-compressor) checkpoint of the GRPO LoRA for vLLM.
Downloads · 30 days
17
28% of all-time downloads
All-time downloads
61
Public
Parameters
3.1B
4.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.7 GB · 100%
How the weights are stored.
BF161.6B · 53%
From the Hugging Face model README
Merged NVFP4 (llm-compressor) checkpoint of the GRPO LoRA for vLLM.
| Metric | Think-SFT | GRPO |
|---|---|---|
| json_ok | 44.4% | 84.1% |
| think_closed | 46.0% | 92.1% |
| mean_jaccard | 0.129 | 0.235 |
| hit_max | 55.6% | 14.3% |
LoRA source: hudsongouge/qwen35-4b-grpo-rescue