EleutherAI / tokengramsLinks
Efficiently computing & storing token n-grams from large corpora
β23Updated 7 months ago
Alternatives and similar repositories for tokengrams
Users that are interested in tokengrams are comparing it to the libraries listed below
Sorting:
- NLP with Rust for Python π¦πβ62Updated 2 weeks ago
- An unofficial implementation of the Infini-gram model proposed by Liu et al. (2024)β33Updated 11 months ago
- β46Updated last week
- Minimum Description Length probing for neural network representationsβ19Updated 4 months ago
- Training hybrid models for dummies.β21Updated 4 months ago
- Training code for Sparse Autoencoders on Embedding modelsβ38Updated 3 months ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.β25Updated 2 years ago
- Code for SaGe subword tokenizer (EACL 2023)β25Updated 6 months ago
- See https://github.com/cuda-mode/triton-index/ instead!β10Updated last year
- gzip Predicts Data-dependent Scaling Lawsβ35Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ββ32Updated last month
- β38Updated 10 months ago
- PageRank for LLMsβ42Updated last month
- Tree-based indexes for neural-searchβ32Updated last year
- Understanding how features learned by neural networks evolve throughout trainingβ34Updated 7 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked promptsβ24Updated last year
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found heβ¦β31Updated last year
- Aioli: A unified optimization framework for language model data mixingβ25Updated 4 months ago
- URL downloader supporting checkpointing and continuous checksumming.β19Updated last year
- Latent Large Language Modelsβ18Updated 9 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limitβ62Updated last year
- β43Updated 3 months ago
- Generate interleaved text and image content in a structured format you can directly pass to downstream APIs.β27Updated 7 months ago
- Code for our EMNLP '22 paper "Fixing Model Bugs with Natural Language Patches"β19Updated 2 years ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning Pβ¦β34Updated last year
- Visualize expert firing frequencies across sentences in the Mixtral MoE modelβ18Updated last year
- β35Updated last month
- Library for fast text representation and classification.β28Updated last year
- Simple GRPO scripts and configurations.β58Updated 3 months ago
- β38Updated last year