|
|
--- |
|
|
license: llama3.2 |
|
|
datasets: |
|
|
- HuggingFaceFW/finepdfs |
|
|
- HuggingFaceM4/FineVision |
|
|
- Helsinki-NLP/opus-100 |
|
|
- facebook/flores |
|
|
- HuggingFaceH4/Multilingual-Thinking |
|
|
- tatsu-lab/alpaca |
|
|
- bigscience/xP3 |
|
|
- allenai/sciq |
|
|
- allenai/c4 |
|
|
- mozilla-foundation/common_voice_17_0 |
|
|
- jhu-clsp/jfleg |
|
|
- bea2019st/wi_locness |
|
|
- fce-m72109/mascorpus |
|
|
- bene-ges/en_cmudict |
|
|
- tobacco/word2vec |
|
|
- allenai/peer_read |
|
|
- openslr/librispeech_asr |
|
|
- EmpathaticEmbodiedAI/EmpathyRobot |
|
|
- conceptnet5/conceptnet5 |
|
|
- antokun/glove.6B.50d |
|
|
- OpenRL/daily_dialog |
|
|
- tetti/spelling-dataset-extended |
|
|
- rajpurkar/squad_v2 |
|
|
- lmms-lab/vocalsound |
|
|
- grammarly/coedit |
|
|
language: |
|
|
- en |
|
|
- zh |
|
|
- fr |
|
|
- es |
|
|
- de |
|
|
- ar |
|
|
- pt |
|
|
- ko |
|
|
- ru |
|
|
- hi |
|
|
- bn |
|
|
- ja |
|
|
- sw |
|
|
--- |