tomaarsen / attention_sinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
☆667Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for attention_sinks
- YaRN: Efficient Context Window Extension of Large Language Models☆1,339Updated 6 months ago
- Code for fine-tuning Platypus fam LLMs using LoRA☆623Updated 9 months ago
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆610Updated 5 months ago
- ☆465Updated 2 months ago
- ☆445Updated last week
- This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and bench…☆582Updated 11 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆787Updated last week
- ☆411Updated last year
- A bagel, with everything.☆312Updated 6 months ago
- batched loras☆336Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,143Updated 3 weeks ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆642Updated 2 months ago
- Official repository for LongChat and LongEval☆512Updated 5 months ago
- Generative Representational Instruction Tuning☆562Updated this week
- Generate textbook-quality synthetic LLM pretraining data☆488Updated last year
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆528Updated 7 months ago
- Codebase for Merging Language Models (ICML 2024)☆765Updated 6 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆553Updated 8 months ago
- Official repository for ORPO☆420Updated 5 months ago
- Automatically evaluate your LLMs in Google Colab☆556Updated 6 months ago
- ☆527Updated 9 months ago
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆881Updated 2 weeks ago
- Official PyTorch implementation of QA-LoRA☆116Updated 7 months ago
- LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions☆811Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆642Updated last month
- Tune any FALCON in 4-bit☆468Updated last year
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆435Updated 7 months ago
- Serving multiple LoRA finetuned LLM as one☆979Updated 6 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆415Updated 10 months ago
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆706Updated 5 months ago