Alternatives and similar repositories for transformer-birth

Users that are interested in transformer-birth are comparing it to the libraries listed below

• sjelassi / transformers_ssm_copy
  ☆35Updated last year
• berlino / seq_icl
  ☆53Updated last year
• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆80Updated 2 years ago
• locuslab / edge-of-stability
  ☆72Updated 11 months ago
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆40Updated 2 years ago
• sustcsonglin / flash-linear-rnn
  Implementations of various linear RNN layers using pytorch and triton
  ☆54Updated 2 years ago
• shauli-ravfogel / rlace-icml
  ☆36Updated 3 years ago
• DeqingFu / transformers-icl-second-order
  Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…
  ☆19Updated last year
• machine-discovery / deer
  Parallelizing non-linear sequential models over the sequence length
  ☆55Updated 4 months ago
• princeton-nlp / LM-Kernel-FT
  A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643
  ☆78Updated 2 years ago
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆61Updated 4 months ago
• p-lambda / incontext-learning
  Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…
  ☆106Updated 2 years ago
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆37Updated 3 weeks ago
• RobertCsordas / ndr
  The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".
  ☆34Updated 5 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆59Updated 2 years ago
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆68Updated last year
• igul222 / plaid
  ☆108Updated 2 years ago
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆62Updated 2 years ago
• KihoPark / linear_rep_geometry
  ☆110Updated 9 months ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Updated last year
• gregorbachmann / Next-Token-Failures
  ☆104Updated last year
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated 2 years ago
• srush / mamba-scans
  Blog post
  ☆17Updated last year
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆64Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆85Updated last year
• RakitinDen / pytorch-recursive-gumbel-max-trick
  Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces, NeurIPS 2021
  ☆13Updated 3 years ago
• radarFudan / Curse-of-memory
  Curse-of-memory phenomenon of RNNs in sequence modelling
  ☆18Updated 6 months ago
• TRAIS-Lab / dattri
  `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
  ☆94Updated last week
• LIONS-EPFL / scion
  ☆47Updated last month
• sustcsonglin / gated_linear_attention_layer
  ☆31Updated last year