metadata
license: apache-2.0
Conversion process:
- Download original weights from https://models.mistralcdn.com/mistral-7b-v0-2/mistral-7B-v0.2.tar
- Convert with https://github.com/huggingface/transformers/blob/main/src/transformers/models/mistral/convert_mistral_weights_to_hf.py
- You may need to copy the tokenizer.model from Mistral-7B-Instruct-v0.2 repo.