README.md

metadata

license: gemma
language:
  - en
tags:
  - mlx
base_model: IlyaGusev/gemma-2-9b-it-abliterated

gemma-2-9b-it-abliterated-mlx-2bit

The Model gemma-2-9b-it-abliterated-mlx-2bit was converted to MLX format from IlyaGusev/gemma-2-9b-it-abliterated using mlx-lm version 0.19.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("gemma-2-9b-it-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)