2 1 10

Harlley Oliveira PRO

harlley

https://github.com/harlley

AI & ML interests

Agentic UI using small local fine-tuned models directly in the browser.

Recent Activity

updated a Space about 18 hours ago

harlley/basic-agentic-ui

new activity 2 days ago

onnx-community/functiongemma-270m-it-ONNX:Small experiment with FunctionGemma and Transformers.js

new activity 3 days ago

google/functiongemma-270m-it:Fine-tuning didn't work after ONNX export

View all activity

Organizations

liked a model 21 days ago

zai-org/AutoGLM-Phone-9B-Multilingual

Image-Text-to-Text • 934k • Updated 23 days ago • 12.8k • • 210

liked a model 3 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 2.86M • • 5.49k

liked a Space 3 months ago

Kokoro Text-to-Speech

🗣

219

High-quality speech synthesis powered by Kokoro TTS

liked a model 3 months ago

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Sep 1, 2025 • 623k • 2.12k

liked a dataset 6 months ago

snorkelai/agent-finance-reasoning

Viewer • Updated Aug 20, 2025 • 357 • 424 • 64

liked a model 9 months ago

canopylabs/orpheus-3b-0.1-pretrained

Text-to-Speech • 4B • Updated Mar 19, 2025 • 5.04k • • 163

liked 4 Spaces over 1 year ago

Whisper Timestamped

🕒

217

In-browser speech recognition w/ word-level timestamps

PixArt Sigma 900M

🖼

153

Generate images from text prompts

OpenGPT 4o

🔥

4.32k

GPT 4o like bot.

Live Portrait

🤪

3.67k

Apply the motion of a video on a portrait