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

This model finetunes the ft model unsloth/orpheus-3b-0.1-ft using the finetuning pipeline. Full finetuning with Unsloth for 1 epochs.

Datasets

vietnhat/us-mpofu-yt-v3,vietnhat/za-lungelo-yt-v1,vietnhat/za-phumlani-yt-v1,vietnhat/za-elana-yt-v1,vietnhat/za-lebo-yt-v1,vietnhat/za-zenande-csm-metadata2-v1,JobixAi/SA-zenande-records

--dataset_ratio 1,1,1,1,1,0.4,0.8

Inference

Available voice (SA): elana, lebo, lungelo, mpofu, phumlani, zenande

temperature = 0.7
top_p = 0.9
repetition_penalty = 1.1
Downloads last month
1
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 JobixAi/tts-yt-multi-za-v2

Quantizations
1 model