Modelpublic

beezu/allura-org_Llama-3.3-70B-Joyous-MLX-MXFP4

sourceHugging Facellama3.3updated 9mo agoView on Hugging Face

0likes20downloads

Model Card

beezu/allura-org_Llama-3.3-70B-Joyous-MLX-MXFP4

This model beezu/allura-org_Llama-3.3-70B-Joyous-MLX-MXFP4 was converted to MLX format from allura-org/Llama-3.3-70B-Joyous using mlx-lm version 0.29.1.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("beezu/allura-org_Llama-3.3-70B-Joyous-MLX-MXFP4")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)