README.md

metadata

datasets:
  - THUDM/LongWriter-6k
language:
  - en
  - zh
library_name: transformers
license: llama3.1
tags:
  - Long Context
  - chatglm
  - llama
  - mlx

shi3z/mlx-LongWriter-llama3.1-8b-8bit

The Model shi3z/mlx-LongWriter-llama3.1-8b-8bit was converted to MLX format from THUDM/LongWriter-llama3.1-8b using mlx-lm version 0.17.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("shi3z/mlx-LongWriter-llama3.1-8b-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)