license: gpl-3.0
datasets:
- Orion-zhen/meissa-unalignments
language: - zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
base_model: Orion-zhen/Qwen2.5-14B-Instruct-Uncensored
tags: - mlx
enet45/Qwen2.5-14B-Instruct-Uncensored-mlx-4Bit
The Model enet45/Qwen2.5-14B-Instruct-Uncensored-mlx-4Bit was converted to MLX format from Orion-zhen/Qwen2.5-14B-Instruct-Uncensored using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("enet45/Qwen2.5-14B-Instruct-Uncensored-mlx-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)