Downloads · 30 days
29
7% of all-time downloads
WaveCut/acestep-5Hz-lm-4B-mlx_8bit
acestep-5Hz-lm-4B-mlx_8bit is a text generation model from WaveCut. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
This model WaveCut/acestep-5Hz-lm-4B-mlx8bit was converted to MLX format from ACE-Step/acestep-5Hz-lm-4B using mlx-lm version 0.30.6.
Downloads · 30 days
29
7% of all-time downloads
All-time downloads
406
Public
Parameters
4.2B
4.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.5 GB · 99%
How the weights are stored.
U324.2B · 100%
From the Hugging Face model README
This model WaveCut/acestep-5Hz-lm-4B-mlx_8bit was converted to MLX format from ACE-Step/acestep-5Hz-lm-4B using mlx-lm version 0.30.6.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("WaveCut/acestep-5Hz-lm-4B-mlx_8bit")
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)