MLX How to use tonidurans/ALIA-40b-instruct-2605-mlx-q4 with MLX:
# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# Generate text with mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("tonidurans/ALIA-40b-instruct-2605-mlx-q4")
prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
text = generate(model, tokenizer, prompt=prompt, verbose=True) 
