tomaarsen / attention_sinksLinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
☆708Updated last year
Alternatives and similar repositories for attention_sinks
Users that are interested in attention_sinks are comparing it to the libraries listed below
Sorting:
- Code for fine-tuning Platypus fam LLMs using LoRA☆628Updated last year
- A bagel, with everything.☆324Updated last year
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆661Updated last year
- ☆416Updated last year
- batched loras☆345Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆423Updated last year
- ☆560Updated 11 months ago
- ☆546Updated 8 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,584Updated last year
- This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and bench…☆593Updated last year
- Official repository for LongChat and LongEval☆527Updated last year
- Tune any FALCON in 4-bit☆466Updated last year
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆957Updated 10 months ago
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆728Updated last year
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆388Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆701Updated last year
- Train Models Contrastively in Pytorch☆738Updated 4 months ago
- ☆536Updated 9 months ago
- Generate textbook-quality synthetic LLM pretraining data☆503Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,272Updated 5 months ago
- The repository for the code of the UltraFastBERT paper☆517Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆461Updated last year
- Inference code for Persimmon-8B☆415Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆719Updated last year
- A repository for research on medium sized language models.☆509Updated 2 months ago
- An open collection of methodologies to help with successful training of large language models.☆506Updated last year
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆557Updated 7 months ago
- Customizable implementation of the self-instruct paper.☆1,049Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆599Updated last year
- Official PyTorch implementation of QA-LoRA☆138Updated last year