license: llama3.3
language:

• en
  widget:
• text: Llama-3.3-8B-Instruct-128K_Abliterated
  output:
  url: https://huggingface.co/SicariusSicariiStuff/Llama-3.3-8B-Instruct-128K_Abliterated/resolve/main/Images/Llama-3.3-8B-Instruct-128K_Abliterated.png
  base_model: SicariusSicariiStuff/Llama-3.3-8B-Instruct-128K_Abliterated
  tags:
• mlx

alexgusevski/Llama-3.3-8B-Instruct-128K_Abliterated-mlx-2Bit

The Model alexgusevski/Llama-3.3-8B-Instruct-128K_Abliterated-mlx-2Bit was converted to MLX format from SicariusSicariiStuff/Llama-3.3-8B-Instruct-128K_Abliterated using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/Llama-3.3-8B-Instruct-128K_Abliterated-mlx-2Bit")

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)