Alternatives and similar repositories for Perceiver-Resampler-XAttn-Captioning

Users that are interested in Perceiver-Resampler-XAttn-Captioning are comparing it to the libraries listed below

• huggingface / m4-logs
  M4 experiment logbook
  ☆57Updated 2 years ago
• ryanwebster90 / snip-dedup
  ☆103Updated last year
• huggingface / chug
  Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.
  ☆159Updated last year
• facebookresearch / clip-rocket
  Code release for "Improved baselines for vision-language pre-training"
  ☆61Updated last year
• SriramB-98 / vit-decompose
  ☆23Updated 9 months ago
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated last year
• facebookresearch / capi
  Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
  ☆122Updated 6 months ago
• apoorvkh / torchrunx
  Easily run PyTorch on multiple GPUs & machines
  ☆47Updated 2 weeks ago
• lucidrains / flash-cosine-sim-attention
  Implementation of fused cosine similarity attention in the same style as Flash Attention
  ☆217Updated 2 years ago
• OATML / RHO-Loss
  ☆210Updated 3 years ago
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• lucidrains / einops-exts
  Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️
  ☆55Updated 2 years ago
• LAION-AI / General-GPT
  ☆65Updated 2 years ago
• jxiw / BiGS
  Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …
  ☆114Updated last year
• patil-suraj / vit-vqgan
  JAX implementation ViT-VQGAN
  ☆82Updated 3 years ago
• bfshi / TOAST
  Official code for "TOAST: Transfer Learning via Attention Steering"
  ☆186Updated 2 years ago
• TomerRonen34 / mixed-resolution-vit
  ☆53Updated 2 years ago
• LAION-AI / laion50BU
  Un-*** 50 billions multimodality dataset
  ☆22Updated 3 years ago
• jiasenlu / LL3M
  LL3M: Large Language and Multi-Modal Model in Jax
  ☆74Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• taesiri / ZoomIsAllYouNeed
  Official code and data for NeurIPS 2023 paper "ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial …
  ☆39Updated last year
• EleutherAI / pilev2
  ☆13Updated 2 years ago
• lucidrains / taylor-series-linear-attention
  Explorations into the recently proposed Taylor Series Linear Attention
  ☆99Updated last year
• sayakpaul / big_vision_experiments
  Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.
  ☆22Updated 2 years ago
• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆80Updated 2 years ago
• facebookresearch / adaptive_scheduling
  Experimental scripts for researching data adaptive learning rate scheduling.
  ☆22Updated 2 years ago
• cloneofsimo / min-fsdp
  ☆91Updated last year
• andravin / spio
  Memory-Efficient CUDA kernels for training ConvNets with PyTorch.
  ☆42Updated 8 months ago
• lucidrains / MaMMUT-pytorch
  Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch
  ☆102Updated 2 years ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆100Updated last year