Original model: https://huggingface.co/ignos/Mistral-T5-7B-v1

At the time of this writting this model scores the higest in the math GSM8K benchmark.

Score: 73.16 https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard

This repo contains the gguf 5-bit quant.

Downloads last month
0
GGUF
Model size
7.24B params
Architecture
llama

5-bit

Inference API
Unable to determine this model's library. Check the docs .