Views
No views yet
GreenBitAI/Qwen3-4B-Thinking-2507-layer-mix-bpw-4.0 using gbx-lm version 0.4.1.
Refer to the original model card for more details on the model.pip install gbx-lm1from gbx_lm import load, generate
2
3model, tokenizer = load("GreenBitAI/Qwen3-4B-Thinking-2507-layer-mix-bpw-4.0-mlx")
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)