metadata

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - reward model
  - RLHF
  - RLAIF
  - mlx
datasets:
  - berkeley-nest/Nectar

mitkox/Starling-LM-7B-beta-RLAIF-4bit-MLX

This model was converted to MLX format from Nexusflow/Starling-LM-7B-beta. 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("mitkox/Starling-LM-7B-beta-RLAIF-4bit-MLX")
response = generate(model, tokenizer, prompt="hello", verbose=True)