InstaDeepAI/multi_species_genomes download history
InstaDeepAI/multi_species_genomes is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 530 times (112 in the last 7 days), and 26,682 times in total. It ranks #31,690 among datasets by monthly downloads.
Dataset made of diverse genomes available on NCBI and coming from ~850 different species. Test and validation are made of 50 species each. The rest of the genomes are used for training. Default configuration "6kbp" yields chunks of 6.2kbp (100bp overlap on each side). Similarly, the "12kbp"configur
Models trained on multi_species_genomes
4 models list it as training data.
- InstaDeepAI/nucleotide-transformer-2.5b-multi-species 3.3K downloads in 30 days
- divyeshkamalanaban/nucleotide-transformer-2.5b-multi-species-NF4-Q4 81 downloads in 30 days
- Iambackup/nucleotide-transformer-2.5b-multi-species 27 downloads in 30 days
- Sharmistha-NLP/mergedna-400M – downloads in 30 days