LSTM, Discrete Flow Matching and Dirichlet Flow Matching weights, training curves, generated DNA and processed datasets for G-quadruplex-associated sequences. The short models generate 13–49-nucleotide cores. The 512- and 1,024-nucleotide models generate genomic regions containing those cores. Unconditional LSTM weights are retained in lstm/unconditional/{short,nt512,nt1024}/. Their old generations have been removed pending retraining on the shared training subset. Tm-conditioned weights are in lstm/conditional/{short,nt512,nt1024}/ and discreteflowmatching/conditional/{short,nt512,nt1024}/, with a loading config beside each model.safetensors. The same flow-matching weights support both…
Independent publisher
Leontenkov Egor
vsemmir13
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers1
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.