license: apache-2.0
language:
- en
- zh
base_model: huihui-ai/Megrez-3B-Instruct-abliterated
pipeline_tag: text-generation
tags: - abliterated
- uncensored
- mlx
- mlx-my-repo
library_name: transformers
mlx-community/Megrez-3B-Instruct-abliterated-6bit
The Model mlx-community/Megrez-3B-Instruct-abliterated-6bit was converted to MLX format from huihui-ai/Megrez-3B-Instruct-abliterated using mlx-lm version 0.20.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Megrez-3B-Instruct-abliterated-6bit")
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)