ZeroGPU Explorers

community

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

cbensimon updated a Space 4 days ago

zero-gpu-explorers/README

rishiraj authored a paper 5 days ago

Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling

indiejoseph authored a paper 7 days ago

HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs

View all activity

cbensimon

updated a Space 4 days ago

README

🌍

kadirnar

posted an update 14 days ago

Post

1713

What can you do with the VyvoTTS library?

- You can train a model in a language it has never been trained in using the PT model. There’s no need for large datasets.
- With the PT model, you can easily replicate the voice of any character you want. Just 1k samples are enough.
- You can add emotion support with a small dataset.

Github: https://github.com/Vyvo-Labs/VyvoTTS
HuggingFace:

Vyvo

mrfakename

in zero-gpu-explorers/README 18 days ago

Limits on PRO account

#88 opened about 1 year ago by

moonslink

EvanTHU

authored 2 papers 19 days ago

Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

Paper • 2508.13139 • Published 21 days ago • 3

Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

Paper • 2508.09131 • Published 27 days ago • 16

mrfakename

in zero-gpu-explorers/README 24 days ago

use authentication in huggingface Gradio API!!!(hosting on ZeroGPU)

❤️ 👀 5

#129 opened 10 months ago by

Nerva1228

ZennyKenny

posted an update 26 days ago

Post

2577

It's just a matter of time before all the data leakage and data scraping associated with building, training, and using AI results in some kind of major scandal.

That's why I think this paper by @spintronic is so important: Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN (2508.06647)

Glad to know that there are already researchers looking to mitigate and address this risk before the s**t hits the fan.

2 replies

Vokturz

posted an update about 1 month ago

Post

400

🤗 A Transformers.js Playground

I just created a new spaces to test models directly in the browser using Transformers.js. You can pick any model from a list (mainly from the onnx-community), or just load the one you desire :) It also allows you to choose among different quantizations!

Currently the following pipelines are supported
- feature-extraction
- image-classification
- text-generation
- text-classification
- text-to-speech
- zero-shot-classification

Vokturz/transformers-js-playground

mrfakename

in zero-gpu-explorers/README 2 months ago

Buy extra ZERO GPU minutes?

#166 opened 2 months ago by

JKM2025

hysts

in zero-gpu-explorers/README 2 months ago

[GPU-Zero] _pickle.PicklingError: Can't pickle local object 'State.init.<locals>.<lambda>'

👀 2

#136 opened 9 months ago by

Mar2Ding

Deadmon

in zero-gpu-explorers/README 2 months ago

ZeroGPU quota exceeded bug

#165 opened 2 months ago by

Korrumz2

cbensimon

posted an update 3 months ago

Post

3586

🚀 ZeroGPU now supports PyTorch native quantization via torchao

While it hasn’t been battle-tested yet, Int8WeightOnlyConfig is already working flawlessly in our tests.

Let us know if you run into any issues — and we’re excited to see what the community will build!

import spaces
from diffusers import FluxPipeline
from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_

pipeline = FluxPipeline.from_pretrained(...).to('cuda')
quantize_(pipeline.transformer, Int8WeightOnlyConfig()) # Or any other component(s)

@spaces.GPU
def generate(prompt: str):
    return pipeline(prompt).images[0]