facebookresearch/atlas
Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)
PythonNOASSERTION
Issues
- 2
Running Atlas on small GPU's.
#11 opened by prasad4fun - 0
- 0
Why is the index size so big?
#22 opened by littlewine - 1
- 1
How can run this code on a normal personal machine? We don't have slurm configured, can we run it by simply modifying the run script?
#21 opened by 1180300528 - 2
Example training script for the KILT task
#19 opened by La-SilverLand - 1
How do you conduct distributed training?
#17 opened by Polymorphy12 - 2
Save and load compressed index
#18 opened by xudongguan202 - 1
Access to the models [fully and 64-shot] fine-tuned on different datasets
#13 opened by ParishadBehnam - 1
Possibility of releasing closed-book Atlas models?
#14 opened by lovhag - 1
Not able to download the NQ data
#16 opened by Tanya-11 - 0
- 5
"RuntimeError: einsum(): operands do not broadcast with remapped shapes [original->remapped]" during reproducing mlm pre-training
#9 opened by Duemoo - 8
Small ATLAS
#7 opened by jamesoneill12 - 1
- 2
"AttributeError: module 'torch.optim.adamw' has no attribute 'F'" in AdamWFP32Copy.py
#5 opened by Duemoo - 1
what is srun?
#1 opened by RevL147