metadata
language:
- en
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- mlx
pipeline_tag: text-generation
mlx-community/Llama-3-8b-64k-PoSE-8bit
This model was converted to MLX format from winglian/Llama-3-8b-64k-PoSE
using mlx-lm version 0.10.0.
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/Llama-3-8b-64k-PoSE-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)