Views
No views yet
1 arc arc/e boolq hswag obkqa piqa wino
2q8-hi 0.550,0.744,0.818,0.700,0.458,0.780,0.6991 arc arc/e boolq hswag obkqa piqa wino
2bf16 0.490,0.674,0.793,0.612,0.416,0.756,0.669
3mxfp8 0.480,0.656,0.797,0.608,0.400,0.755,0.665pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("Gemma-4-E4B-it-Fable-Distill-q8-hi-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, return_dict=False,
11 )
12
13response = generate(model, tokenizer, prompt=prompt, verbose=True)