license: apache-2.0
base_model: jenerallee78/Ministral-3-14B-abliterated
tags:
- abliteration
- uncensored
- mistral
- ministral
- 14b
- mlx
- mlx-my-repo
language: - en
library_name: transformers
pipeline_tag: text-generation
McG-221/Ministral-3-14B-abliterated-mlx-8Bit
The Model McG-221/Ministral-3-14B-abliterated-mlx-8Bit was converted to MLX format from jenerallee78/Ministral-3-14B-abliterated using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("McG-221/Ministral-3-14B-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)