14 lines
348 B
Python
14 lines
348 B
Python
from mlx_lm import generate, load
|
|
|
|
model, tokenizer = load("mlx-community/Qwen3.5-4B-OptiQ-4bit")
|
|
|
|
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)
|
|
|
|
print(text)
|