Downloads · 30 days
23
7% of all-time downloads
dotyerts/Apodex-1.0-4B-SFT-mlx-4Bit
Apodex-1.0-4B-SFT-mlx-4Bit is a text generation model from dotyerts. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
The Model dotyerts/Apodex-1.0-4B-SFT-mlx-4Bit was converted to MLX format from apodex/Apodex-1.0-4B-SFT using mlx-lm version 0.31.2.
Downloads · 30 days
23
7% of all-time downloads
All-time downloads
324
Public
Parameters
4.2B
2.4 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors2.4 GB · 99%
How the weights are stored.
U324.2B · 100%
From the Hugging Face model README
The Model dotyerts/Apodex-1.0-4B-SFT-mlx-4Bit was converted to MLX format from apodex/Apodex-1.0-4B-SFT using mlx-lm version 0.31.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("dotyerts/Apodex-1.0-4B-SFT-mlx-4Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)