barozp/Qwen3.8-27B-Opus-Distill

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Link finished GGUF repo instead of upcoming placeholder

add video_preprocessor_config.json (missing after text-only save_pretrained)

add preprocessor_config.json (missing after text-only save_pretrained)

Update model card: benchmark table + GPQA/ARC caveats + quick start

fix config.json: restore nested text_config + model_type=qwen3_5 (was flat qwen3_5_text)

Opus reasoning distill (LoRA merge) + native vision + native MTP carried over

initial commit