language: en
tags:
- mlx
pipeline_tag: text-generation
library_name: mlx
kang-heewon/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-MLX-8bit
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("kang-heewon/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-MLX-8bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)