cogbuji/OpenHermes-2.5-Mistral-7B-mlx-4bit

This model was converted to MLX format from teknium/OpenHermes-2.5-Mistral-7B and quantized. Refer to the original model card for more details on the model.

It was converted and quantized with mlx 0.7.0 and mlx_lm 0.3.0 and should be used with those versions. Later versions of these may deprecate this model

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cogbuji/OpenHermes-2.5-Mistral-7B-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)