The Model SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic-mlx-5Bit was converted to MLX format from SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic using mlx-lm version 0.31.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("SolsticeAI/Arete-27B-Unlocked-Uncensored-Heretic-mlx-5Bit")
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)
model-00001-of-00004.safetensors 5.4 GBmodel-00003-of-00004.safetensors 5.4 GBmodel-00002-of-00004.safetensors 5.3 GBmodel-00004-of-00004.safetensors 2.4 GB