Hugging Face's logo
Himanshu Pal's picture

Himanshu Pal

hmnshpl
2
TaoDoggy's profile picture
ยท

AI & ML interests

NLP, TDL

Recent Activity

reacted to loubnabnl's post with ๐Ÿ”ฅ 4 days 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
upvoted a paper 2 months ago
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
authored a paper 5 months ago
LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs
View all activity

Organizations

TeachingTraining's profile picture