The Model
andosen/Psych_Qwen_32B-mlx-5Bit was converted to MLX format from
Compumacy/Psych_Qwen_32B using mlx-lm version
0.31.2.
1from mlx_lm import load, generate
2
3model, tokenizer = load("andosen/Psych_Qwen_32B-mlx-5Bit")
4
5prompt="hello"
6
7if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
8 messages = [{"role": "user", "content": prompt}]
9 prompt = tokenizer.apply_chat_template(
10 messages, tokenize=False, add_generation_prompt=True
11 )
12
13response = generate(model, tokenizer, prompt=prompt, verbose=True)
