llm
llm copied to clipboard
Implement MPT Model
Closes #214.
Tested with https://huggingface.co/LLukas22/mpt-7b-ggml
I can't find a Replit model to test with.
This is good to go, but will produce garbage output after a few tokens without this fix to ggml https://github.com/ggerganov/ggml/pull/145/files#diff-b4a500ab2765c31526c5541f3e51e21e46990b87d9774cac6f3089db315bdc5b
We'll have to wait for https://github.com/ggerganov/ggml/pull/145 to be merged.
65k token context here we come
Sounds like this is all good to go! @danforbes Does this include all of the changes from the ggml PR?