Downloads · 30 days
110
3% of all-time downloads
mlx-community/Hunyuan-A52B-Instruct-3bit
Hunyuan-A52B-Instruct-3bit is a text generation model from mlx-community. Use it when you need the model to write or continue text. It is set up for transformers.
The Model mlx-community/Hunyuan-A52B-Instruct-3bit was converted to MLX format from tencent-community/Hunyuan-A52B-Instruct using mlx-lm version 0.19.3.
Downloads · 30 days
110
3% of all-time downloads
All-time downloads
3.5K
Public
Parameters
389B
194 GB on disk
Likes
5
Public
Click a slice to open those files.
.safetensors194 GB · 100%
How the weights are stored.
U32389B · 100%
From the Hugging Face model README
The Model mlx-community/Hunyuan-A52B-Instruct-3bit was converted to MLX format from tencent-community/Hunyuan-A52B-Instruct using mlx-lm version 0.19.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Hunyuan-A52B-Instruct-3bit")
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)