UCSC-VLAA / CLIPA

[NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"

UCSC-VLAA/CLIPA Issues

Evaluation when reducing text token
Updated 2 months ago1
Inference Code
Closed 3 months ago1
Training is too slow
Closed 3 months ago2
What's the lr for ViT-H/14 in pre-training
Closed 3 months ago1
Discrepancy in Zero-Shot Top-1 Accuracy for ViT-H/14 Replication
Closed 8 months ago3
Can't use multiple XLA devices when using PyTorch XLA
Closed a year ago2
Invalid pointer error on torch XLA
Closed a year ago1
How do you manage the positional embeddings for different image resolution?
Closed a year ago1
How to download gs://vit_models/lit/bert/uncased_L-12_H-768_A-12/vocab.txt?
Closed a year ago3
How about releasing the weights of models with small input size
Closed a year ago1
CLIP ViT-S/16 model weights
Closed a year ago1