mlx-community/3b-zh-pretrain-research_release-8bit

This model was converted to MLX format from canopylabs/3b-zh-pretrain-research_release using mlx-vlm version 0.0.3. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-audio

python -m mlx_audio.tts.generate --model mlx-community/3b-zh-pretrain-research_release-8bit --text "Hello, world"

Safetensors

Model size

928M params

Tensor type

FP16

U32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Finetuned

(385)

this model