전체 검색

AI 모델 84759

• data2vec-text-base↗

  facebook

• hiera_small_224.mae_in1k_ft_in1k↗

  facebook

• mms-tts-mzi↗

  facebook

• MobileLLM-ParetoQ-350M-BF16↗

  facebook

• wav2vec2-xls-r-300m-en-to-15↗

  facebook

• pokemon-showdown-agent-v6-Q4_K_M-GGUF↗

  FedericoHeichou

• illuma↗

  fuhaddesmond

• stable-diffusion-3.5-medium-GGUF↗

  gaianet

• byt5-base↗

  Google

  ByT5 is a tokenizer-free version of Google's T5 and generally follows the architecture of MT5. ByT5 was only pre-trained on mC4 excluding any supervised training with an average span-mask of 20 UTF-8 characters. Therefore, this model has to be fine-tuned before it is useable on a downstream task. ByT5 works especially well on noisy text data,*e.g.*, `google/byt5-base` significantly outperforms mt5-base on TweetQA.

• roberta2roberta_L-24_discofuse↗

  Google