metadata

language:
  - en
  - th
license: llama3
tags:
  - instruct
  - chat
  - mlx
pipeline_tag: text-generation

mlx-community/typhoon-v1.5-8b-instruct-4bit-mlx

This model was converted to MLX format from scb10x/typhoon-v1.5-8b-instruct 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/typhoon-v1.5-8b-instruct-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)