5 12 48

Aidy Osu

aidystark

AI & ML interests

Vision;Language;Speech

Recent Activity

upvoted a collection 14 days ago

Orpheus TTS

liked a model about 1 month ago

slprl/slam

liked a model about 1 month ago

saheedniyi/YarnGPT

View all activity

Organizations

aidystark's activity

upvoted a collection 14 days ago

Orpheus TTS

Collection

TTS Towards Human-Sounding Speech • 2 items • Updated 15 days ago • 52

liked 2 models about 1 month ago

slprl/slam

Audio-to-Audio • Updated Feb 25 • 350 • 10

saheedniyi/YarnGPT

Text-to-Speech • Updated 20 days ago • 460 • 31

commented a paper about 1 month ago

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

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

liked a Space about 1 month ago

2.4k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

commented a paper about 1 month ago

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

Paper • 2502.12115 • Published Feb 17 • 43 •

liked a model about 2 months ago

fishaudio/fish-speech-1.5

Text-to-Speech • Updated 9 days ago • 9.41k • 518

published a model 2 months ago

aidystark/auto-insurance

Updated Oct 4, 2024

liked 2 Spaces 3 months ago

Talk To Ultravox

⚡

Talk to Fixie.ai's Ultravox with WebRTC ⚡️

475

Fish Speech 1

🏆

Generate speech from text

liked 2 models 4 months ago

Qwen/Qwen2-VL-7B-Instruct

Image-Text-to-Text • Updated Feb 6 • 1.26M • • 1.17k

Qwen/Qwen2-VL-2B

Image-Text-to-Text • Updated Dec 6, 2024 • 47.8k • 39

reacted to merve's post with 🚀 4 months ago

Post

2685

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