tomreichel

llemma-7b-extratok

tomreichel/llemma-7b-extratok

llemma-7b-extratok is a text generation model from tomreichel. Use it when you need the model to write or continue text. It is set up for transformers.

Shockingly, loading a model then expanding the language head works but loading a model in 4 bit and then expanding the language head... doesn't seem to work.