Trần Nhật Quý

Fine tune flan t5 xl and flan t5 xxl using qlora and has a problem with learning rate 0.0 and loss 0.0 ?

5

Fine tune flan t5 xl and flan t5 xxl using qlora and has a problem with learning rate 0.0 and loss 0.0 ? Can anyone resolve this problem ? Thanks

Support yarn 128k model

4

Can ctranslate2 support convert yarn 128k model Link to the model: https://huggingface.co/NousResearch/Yarn-Llama-2-13b-128k

Relation extraction triplet

2

can you check the re triplet test with api ? It's like copying from ner code