Hugging Face's logo
Smoliakov's picture
50 24 524

Smoliakov

Yehor
Andrewgarhard300's profile picture Olemara's profile picture patriotyk's profile picture
·
https://t.me/doing_something

AI & ML interests

Speech-to-Text, Text-to-Speech, Voice over Internet Protocol

Recent Activity

repliedto MaziyarPanahi's post 1 day ago
We annotated 119K medical images with two frontier VLMs (Qwen 3.5, Kimi K2.5), cross-validated at 93% agreement, and produced 110K training records, all for under $500. Fine-tuning 3 small models (2-3B params) improved all benchmarks: best model reaches +15.0% average exact match. Everything is open-sourced: datasets, adapters, and code. https://huggingface.co/blog/OpenMed/synthvision
reacted to MaziyarPanahi's post with 🔥 1 day ago
We annotated 119K medical images with two frontier VLMs (Qwen 3.5, Kimi K2.5), cross-validated at 93% agreement, and produced 110K training records, all for under $500. Fine-tuning 3 small models (2-3B params) improved all benchmarks: best model reaches +15.0% average exact match. Everything is open-sourced: datasets, adapters, and code. https://huggingface.co/blog/OpenMed/synthvision
updated a dataset 12 days ago
Yehor/ukr-news
View all activity

Organizations

Karaoke POC's profile picture Speech-UK initiative's profile picture MedVoice's profile picture Call Recognition System's profile picture UA-LAWYER's profile picture SaaS Things's profile picture UDS Bootcamp's profile picture