license: apache-2.0
base_model_relation: finetune
library_name: transformers
base_model: huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated
tags:
- qwen3_6
- token-efficient
- efficient-thinking
- abliterated
- uncensored
- huihui
- mlx
- mlx-my-repo
McG-221/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-mlx-8Bit
The Model McG-221/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-mlx-8Bit was converted to MLX format from huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("McG-221/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-mlx-8Bit")
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)