plantcad/synthetic-genomes-plantcad2-c4096
收藏官方服务:
资源简介:
--- license: apache-2.0 tags: - biology - DNA - genomics - synthetic --- # Synthetic Genomes PlantCAD2 (4096bp) Synthetic DNA sequences from randomly initialized Qwen2 using PlantCAD2 tokenizer. ## Details - Model: Qwen/Qwen2-1.5B (random weights) - Tokenizer: kuleshov-group/PlantCAD2-Small-l24-d0768 - Method: Teacher-forced parallel generation (single forward pass) - Length: 4096bp ## Splits | Split | Count | |-------|-------| | train | 2,638,656 | | validation | 329,832 |
提供机构:
plantcad


