chavez

ma1sd fails to build when architecture is ARM64

2

ma1sd fails to build when the architecture is set to ARM64. It first throws "detected dubious ownership in repository" when checking the folder, then when #2008 is done (both `git...

Add options and local inference

1

Added options to: - Disable Inference (it consumes about 2gb of VRAM even when not active) - Disable wandb and: - if no hftoken is provided it just fills it...

[Request] image_from_spectrogram function

1

As discused in the discord, this could be useful for Audio2Audio

Documentation

1

First of all, thank you for making compilation much simpler. However, I think proper documentation is needed for better adoption of this technology More specifically the `infer_trt` function on https://github.com/VoltaML/voltaML-fast-stable-diffusion/blob/f3db5838bcba7a9f6ae207061ac4ec9ba790b45f/volta_accelerate.py#L446...

Fine-Tuning very slow (6h->24h??)

3

Hello, first of all thank you for releasing the training code for alpaca, we really appreaciate it. I am running the fine-tuning script on an 4xA100-SXM4-80GB, and currently getting an...

Multi-GPU bug?

11

```python Traceback (most recent call last): File "/workspace/alpaca-lora/finetune.py", line 95, in trainer.train(resume_from_checkpoint=False) File "/workspace/miniconda3/lib/python3.10/site-packages/transformers/trainer.py", line 1628, in train return inner_training_loop( File "/workspace/miniconda3/lib/python3.10/site-packages/transformers/trainer.py", line 1895, in _inner_training_loop tr_loss_step = self.training_step(model, inputs)...

ValueError: ConstantTensor's maximum size is not equal to len(data)!

1

Getting the following: ``` ValueError: ConstantTensor's maximum size is not equal to len(data)! Got len(data)=75890688, but expected at least 101187584 bytes. Check that the ConstantTensor's size and dtype are correct....

Example use case of `compute_predictions`?

1

I am trying in the followng way: ```python model = MusicGen.get_pretrained('small') attributes, _ = model._prepare_tokens_and_attributes(["sample text"], None) conditions = attributes null_conditions = ClassifierFreeGuidanceDropout(p=1.0)(conditions) conditions = conditions + null_conditions tokenized =...

[Feature Request] Network Statistics

4

**Is your feature request related to a problem? Please describe.** No. **Describe the solution you'd like** Basically display 2 stats: 1.- Network Input/Output in mbps 2.- Live count of gradient...

Address #15