language:
- en
- fr
- de
- es
- it
- pt
- zh
- ja
- ru
- ko
license: apache-2.0
library_name: vllm
inference: false
base_model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
extra_gated_description: If you want to learn more about how we process your personal
data, please read our Privacy Policy.
tags: - abliterated
- uncensored
- transformers
- mlx
- mlx-my-repo
KYUNGYONG/Mistral-Small-24B-Instruct-2501-abliterated-4bit
The Model KYUNGYONG/Mistral-Small-24B-Instruct-2501-abliterated-4bit was converted to MLX format from huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated using mlx-lm version 0.21.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("KYUNGYONG/Mistral-Small-24B-Instruct-2501-abliterated-4bit")
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)