---
license: apache-2.0
language:
- 'no'
- nb
---

## NoraMistral-7B-warm-instruct-GGUF
- Original model: [NorMistral-7b-warm-instruct](https://huggingface.co/norallm/normistral-7b-warm-instruct)
- Base model: - [NorMistral-7b-warm](https://huggingface.co/norallm/normistral-7b-warm) -- an LLM initialized from [Mistral-7b-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)

This repo contains GGUF formatted files for the instrucation model. <br>
With the added pre-tokenizer `ggml-vocab-normistral-7b-warm.gguf`. <br>
This should remove the warning you will otherwise get in llama.cpp with the original gguf files. 

## ⚠️⚠️
To take advantage of this, changes also needs to be made directly in [llama.cpp](https://github.com/ggerganov/llama.cpp).
- See and example of this here: [GitHub](https://github.com/ggerganov/llama.cpp/commit/921e2c3e63e63f7c7efe168883ec2ac090f62c14).