Locutusque

/

TinyMistral-248M-v2-Instruct

like 7

How good is it when compared to Locutusque/TinyMistral-248M-v2.5-Instruct ?

quants coming? preferably gguf.

The other model you pointed out follows instructions better than this model. This one requires more prompt engineering, but performs better.

I might quantize this model, but I'm sure someone like @Felladrin or @afrideva would quantize this model.

GGUF files are now available at https://huggingface.co/M4-ai/TinyMistral-248M-v2-Instruct-GGUF 🙌