srush / do-we-need-attentionLinks
โ166Updated 2 years ago
Alternatives and similar repositories for do-we-need-attention
Users that are interested in do-we-need-attention are comparing it to the libraries listed below
Sorting:
- Understand and test language model architectures on synthetic tasks.โ221Updated last month
- A MAD laboratory to improve AI architecture designs ๐งชโ124Updated 8 months ago
- some common Huggingface transformers in maximal update parametrization (ยตP)โ82Updated 3 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ152Updated last month
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023โ136Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amountโฆโ53Updated last year
- [NeurIPS 2023] Learning Transformer Programsโ163Updated last year
- Large scale 4D parallelism pre-training for ๐ค transformers in Mixture of Experts *(still work in progress)*โ87Updated last year
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE โฆโ114Updated last year
- nanoGPT-like codebase for LLM trainingโ102Updated 3 months ago
- Language models scale reliably with over-training and on downstream tasksโ98Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPTโ220Updated last year
- โ53Updated last year
- โ37Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAXโ86Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ240Updated 2 months ago
- โ87Updated last year
- โ118Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ130Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"โ81Updated 9 months ago
- Inference code for LLaMA models in JAXโ118Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)โ78Updated last year
- JAX implementation of the Llama 2 modelโ219Updated last year
- Recurrent Memory Transformerโ150Updated 2 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)โ80Updated last year
- Experiment of using Tangent to autodiff tritonโ80Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorchโ229Updated 11 months ago
- โ56Updated 10 months ago
- Implementation of the Llama architecture with RLHF + Q-learningโ166Updated 6 months ago
- Annotated version of the Mamba paperโ487Updated last year