README.md

metadata

license: apache-2.0
base_model: nidum/Nidum-Llama-3.2-3B-Uncensored
library_name: adapter-transformers
tags:
  - chemistry
  - biology
  - legal
  - code
  - medical
  - finance
  - mlx
pipeline_tag: text-generation

nidum/Nidum-Llama-3.2-3B-Uncensored-MLX-4bit

The Model nidum/Nidum-Llama-3.2-3B-Uncensored-MLX-4bit was converted to MLX format from nidum/Nidum-Llama-3.2-3B-Uncensored using mlx-lm version 0.19.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("nidum/Nidum-Llama-3.2-3B-Uncensored-MLX-4bit")

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)