Model fine-tuned on MS-MARCO for 4 epochs.
Starting model: jmvcoelho/t5-base-marco-crop-pretrain-2048
Training script: https://github.com/cxcscmu/LongEmbeddingAnalysis/blob/main/scripts/train_dr.sh
T5ForConditionalGenerationRoPE class: https://github.com/cxcscmu/LongEmbeddingAnalysis/blob/main/OpenMatch/src/openmatch/modeling/rope_t5.py
- Downloads last month
- 6