README.md

metadata

base_model: VincentGOURBIN/Llama-3.2-3B-Fluxed
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - mlx
license: apache-2.0
language:
  - en

mlx-community/Llama-3.2-3B-Fluxed

The Model mlx-community/Llama-3.2-3B-Fluxed was converted to MLX format from VincentGOURBIN/Llama-3.2-3B-Fluxed using mlx-lm version 0.19.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3.2-3B-Fluxed")

prompt="hello"

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

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