Kadir Nar

Results 229 comments of Kadir Nar

Are you planning to work on training with the FP8 model?

@search620 Why don't you publish a demo on the HuggingFace platform? It would be really great. Thanks

@smlkdev I am training the melotts model with sentiment data. But I couldn't get the tensorboard graphs to work. Can you share your sample code?

These are written in the train.log file. Training is still ongoing. Are these important? ```bash 2024-11-19 09:22:10,339 example ERROR enc_p.language_emb.weight is not in the checkpoint 2024-11-19 09:22:10,340 example ERROR emb_g.weight...

@jeremy110 https://huggingface.co/datasets/reach-vb/jenny_tts_dataset I am training this dataset. I made 10 epochs from the config settings. There is epoch 30 in the train.log file and it is still training. What should...

@Tcc0403 You need to run the preprocess code before training the Zac dataset. I did it for the Emilia-De dataset. You can train using this code and config files. Install:...

@comfyanonymous @buzzjeux , Despite using a small LoRA, there's an incredible VRAM increase. I tested it in Diffusers and this issue doesn't occur there. ComfyUI: Txt2Img(Flux) + LoRA: 44GB Diffusers:...

@farzadab , Are there any updates on this issue?

> @kadirnar this was simply a proof of concept. Unfortunately, combining vision into Ultravox is not part of our roadmap. > > What is your use-case? I want to create...

Please add full-finetuning support in float16 format.