Qwen35 4b NVFP4 Podcast Cleaner Grpo
Merged NVFP4 (llm-compressor) checkpoint of the GRPO LoRA for vLLM.
Modellquelle
- Art
- Text model
- Dateigröße
- 4,41 GB
- Basismodell
- Qwen/Qwen3.5-4B
- Version
- vmodel
- Aktualisiert
- 5. Nov. 2026
- Downloads
- 12
- Quelle
- Hugging Face
Quellenbeschreibung
qwen35-4b-nvfp4-podcast-cleaner-grpo
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
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 5. Nov.
Download files
Repository files
File inventory only; completeness is unverified.
Modellartefakte
1 Artefakt
Modellartefakte
1 ArtefaktQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- library_name: transformers base_model: Qwen/Qwen3.5-4B tags: - qwen3.5 - nvfp4 - grpo - llm-compressor - podcast-transcripts license: apache-2.0 --- # qwen35-4b-nvfp4-podcast-cleaner-grpo 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`
Source context: 12 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo hudsongouge/qwen35-4b-nvfp4-podcast-cleaner-grpo
Source context: 10 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo hudsongouge/qwen35-4b-nvfp4-podcast-cleaner-grpo
