How to use tinytrashlabs/dia2-2b-mlx-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download tinytrashlabs/dia2-2b-mlx-8bit --local-dir dia2-2b-mlx-8bit
How to use tinytrashlabs/dia2-2b-mlx-8bit with Dia2:
from dia2 import Dia2, GenerationConfig, SamplingConfig dia = Dia2.from_repo("tinytrashlabs/dia2-2b-mlx-8bit", device="cuda", dtype="bfloat16") config = GenerationConfig( cfg_scale=2.0, audio=SamplingConfig(temperature=0.8, top_k=50), use_cuda_graph=True, ) result = dia.generate("[S1] Hello Dia2!", config=config, output_wav="hello.wav", verbose=True)
https://huggingface.co/tinytrashlabs/dia2-2b-mlx-8bit/resolve/main/tokenizer.json
hf download hf://tinytrashlabs/dia2-2b-mlx-8bit/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/tinytrashlabs/dia2-2b-mlx-8bit/resolve/main/tokenizer.json
