README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - mlx
datasets:
  - openbmb/UltraFeedback
pipeline_tag: text-generation

mlx-community/Mistral7B-PairRM-SPPO-Iter3-unquantized

This model was converted to MLX format from UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3 using mlx-lm version 0.12.1. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral7B-PairRM-SPPO-Iter3-unquantized")
response = generate(model, tokenizer, prompt="hello", verbose=True)