Alternatives and similar repositories for pilev2:

Users that are interested in pilev2 are comparing it to the libraries listed below

• lucidrains / memory-editable-transformer
  My explorations into editing the knowledge and memories of an attention network
  ☆34Updated 2 years ago
• renll / SeqBoat
  [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
  ☆36Updated last year
• EleutherAI / semantic-memorization
  ☆44Updated 5 months ago
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated 11 months ago
• allenai / bff
  ☆38Updated last year
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated 7 months ago
• google-research-datasets / QAmeleon
  QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…
  ☆34Updated last year
• LAION-AI / riverbed
  Tools for content datamining and NLP at scale
  ☆43Updated 10 months ago
• CERC-AAI / Robin
  ☆63Updated 7 months ago
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆37Updated last year
• facebookresearch / adaptive_scheduling
  Experimental scripts for researching data adaptive learning rate scheduling.
  ☆23Updated last year
• google-research / jestimator
  Amos optimizer with JEstimator lib.
  ☆82Updated 11 months ago
• applicaai / CCpdf
  Index of URLs to pdf files all over the internet and scripts
  ☆23Updated 2 years ago
• UKPLab / on-emergence
  Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning
  ☆33Updated 3 months ago
• huggingface / m4-logs
  M4 experiment logbook
  ☆57Updated last year
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆45Updated 9 months ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆96Updated last year
• allenai / easy-to-hard-generalization
  Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"
  ☆47Updated last year
• jxiw / BiGS
  Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …
  ☆116Updated last year
• guy-dar / embedding-space
  ☆54Updated last year
• yikangshen / megablocks
  ☆20Updated 11 months ago
• codekansas / rwkv
  RWKV model implementation
  ☆37Updated last year
• cloneofsimo / zeroshampoo
  ☆33Updated 7 months ago
• crowsonkb / dice-mc
  DiCE: The Infinitely Differentiable Monte-Carlo Estimator
  ☆31Updated last year
• sunyt32 / torchscale
  Transformers at any scale
  ☆41Updated last year
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆80Updated 3 years ago
• google-research-datasets / swim-ir
  SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…
  ☆48Updated last year
• srush / tangent
  Source-to-Source Debuggable Derivatives in Pure Python
  ☆15Updated last year
• HazyResearch / embroid
  Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
  ☆11Updated last year
• kaiokendev / cutoff-len-is-context-len
  Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit
  ☆63Updated last year