metadata
thumbnail: >-
https://cdn-uploads.huggingface.co/production/uploads/67c10cfba43d7939d60160ff/uZgMD4PKMrZQ3oPjhb0gj.jpeg
language:
- en
license: apache-2.0
license_name: m
license_link: https://github.com/QwenLM/Qwen/blob/main/LICENSE
inference: false
tags:
- nsfw
- explicit
- roleplay
- unaligned
- dangerous
- mlx
- mlx-my-repo
base_model: Mawdistical/Lycanthropic-Thoughts-32B
Cozmicalz/Lycanthropic-Thoughts-32B-mlx-2Bit
The Model Cozmicalz/Lycanthropic-Thoughts-32B-mlx-2Bit was converted to MLX format from Mawdistical/Lycanthropic-Thoughts-32B using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Cozmicalz/Lycanthropic-Thoughts-32B-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)