5 11 47

Aidy Osu

aidystark

AI & ML interests

Vision;Language;Speech

Recent Activity

liked a model about 21 hours ago

saheedniyi/YarnGPT

commented on a paper about 22 hours ago

Distilling an End-to-End Voice Assistant Without Instruction Training Data

liked a Space 2 days ago

nanotron/ultrascale-playbook

View all activity

Organizations

aidystark's activity

liked a model about 21 hours ago

saheedniyi/YarnGPT

Text-to-Speech • Updated 25 days ago • 1.14k • 25

commented a paper about 22 hours ago

Distilling an End-to-End Voice Assistant Without Instruction Training Data

Paper • 2410.02678 • Published Oct 3, 2024 • 23 •

liked a Space 2 days ago

1.36k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

commented a paper 5 days ago

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Paper • 2502.12115 • Published 6 days ago • 41 •

liked a model 19 days ago

fishaudio/fish-speech-1.5

Text-to-Speech • Updated Dec 3, 2024 • 11.3k • 480

published a model 24 days ago

aidystark/auto-insurance

Updated Oct 4, 2024

liked 2 Spaces 2 months ago

Talk To Ultravox

⚡

Talk to Fixie.ai's Ultravox with WebRTC ⚡️

446

Fish Speech 1

🏆

Generate speech from text

liked 2 models 3 months ago

Qwen/Qwen2-VL-7B-Instruct

Image-Text-to-Text • Updated 17 days ago • 1.52M • • 1.13k

Qwen/Qwen2-VL-2B

Image-Text-to-Text • Updated Dec 6, 2024 • 19.9k • 34

reacted to merve's post with 🚀 3 months ago

Post

2678

small but mighty 🔥
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb