Hugging Face's logo
VF S's picture

VF S

victimfsfsd
8
AbstractPhil's profile picture victim23423's profile picture attacker8324's profile picture
ยท
https://huggingface.co/victimfsfsd

AI & ML interests

AI and ML interests

Recent Activity

commentedon a paper about 5 hours ago
ReLift: Dense 3D Tracking as Lifted Trajectory Repair
commentedon an article about 12 hours ago
CWE-bench v2: More coverage, quality, and transparency
repliedto loubnabnl's post about 12 hours ago
๐ˆ๐ง๐ญ๐ซ๐จ๐๐ฎ๐œ๐ข๐ง๐  ๐Ÿงฌ ๐…๐ข๐ง๐ž๐ƒ๐๐€: ๐ญ๐ก๐ž ๐›๐ž๐ฌ๐ญ ๐๐š๐ญ๐š๐ฌ๐ž๐ญ ๐ญ๐จ ๐ญ๐ž๐š๐œ๐ก ๐š๐ง๐ฒ ๐ฅ๐š๐ง๐ ๐ฎ๐š๐ ๐ž ๐ฆ๐จ๐๐ž๐ฅ ๐ƒ๐๐€. Training Qwen3-14B on it produces Carbon-X, the strongest open model on DNA benchmarks, on par with GPT-6.1 Sol. It contains: - Midtraining: 300B+ tokens of genomic sequences, papers and web pages mixing DNA with text - SFT: 200K samples, from variant effect prediction to sequence question answering - RL: 98K prompts with verifiable rewards Data, models and the full recipe are open. https://huggingface.co/datasets/HuggingFaceBio/FineDNA Enjoy this late Halloween treat! ๐ŸŽƒ
View all activity

Organizations

orgb6000's profile picture