ollama / ollama

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
https://ollama.com
MIT License
96.36k stars 7.65k forks source link

Aya by Cohere - mt5-xxl arch #3689

Open oliviermills opened 6 months ago

oliviermills commented 6 months ago

What model would you like?

https://huggingface.co/CohereForAI/aya-101

See discussion re t5 and gguf attempts here: https://huggingface.co/CohereForAI/aya-101/discussions/12 trial: https://huggingface.co/kcoopermiller/aya-101-GGUF (using candle)

barrelltech commented 6 months ago

Would also love to see this!

gtlYashParmar commented 5 months ago

Would love to see Aya-101

misutoneko commented 2 months ago

aya-101 works in llama.cpp now, but I guess this tritiumoxide's note about porting llama.cpp stuff to ollama applies. Not a ollama user myself, just a PSA in case anyone wants to give it a try :)