YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Experimental. Trained using only RL (GRPO), no SFT. It doesn't work. Probably needs SFT. Goal is to have it follow the emotion direction.

Safetensors

Model size

3B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for mrfakename/VA-TTS-RL-Only

Quantizations