Views
No views yet
pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("Bogdan01m/RuadaptQwen3-32B-Instruct-MLX-4bit")
4
5prompt = "hello"
6
7if tokenizer.chat_template is not None:
8 messages = [{"role": "user", "content": prompt}]
9 prompt = tokenizer.apply_chat_template(
10 messages, add_generation_prompt=True
11 )
12
13response = generate(model, tokenizer, prompt=prompt, verbose=True)1@article{tikhomirov2024facilitating,
2 title={Facilitating Large Language Model Russian Adaptation with Learned Embedding Propagation},
3 author={Tikhomirov, Mikhail and Chernyshov, Daniil},
4 journal={Journal of Language and Education},
5 volume={10},
6 number={4},
7 pages={130--145},
8 year={2024}
9}