This model beezu/zerofata_MS3.2-PaintedFantasy-v4-24B-MLX-BF16 was converted to MLX format from zerofata/MS3.2-PaintedFantasy-v4-24B using mlx-lm version 0.30.6.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("beezu/zerofata_MS3.2-PaintedFantasy-v4-24B-MLX-BF16")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
model-00004-of-00010.safetensors 5.2 GBmodel-00008-of-00010.safetensors 5.2 GBmodel-00007-of-00010.safetensors 5.2 GBmodel-00005-of-00010.safetensors 5.2 GBmodel-00002-of-00010.safetensors 5.2 GBmodel-00006-of-00010.safetensors 5.1 GBmodel-00003-of-00010.safetensors 5.1 GBmodel-00001-of-00010.safetensors 5.1 GBmodel-00009-of-00010.safetensors 4.3 GBmodel-00010-of-00010.safetensors 1.3 GB有文件?提交种子。
提交种子