FOXAI SEARCH
전체 검색
AI 모델 84761
- DumBot↗
deepparag
- HuggingFaceH4.zephyr-7b-beta-GGUF↗
DevQuasar-8
- Qwen-2.5-Coder-7B↗
EasierAI
- kobart-summary-v3↗
EbanLee
- NVILA-Lite-15B-hf↗
Efficient-Large-Model
- Ostrich-27B-Qwen3.5-260305-GGUF↗
etemiz
- mms-tts-gai↗
facebook
- textless_sm_fr_en↗
facebook
- wmt19-en-de↗
facebook
Pretrained weights were left identical to the original model released by fairseq. For more details, please, see the paper. The score is slightly below the score reported by `fairseq`, since `transformers`` currently doesn't support: - model ensemble, therefore the best performing checkpoint was ported (``model4.pt``). - re-ranking note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
- Qwen3.6-27B-GGUF↗
Fastiraz
