tomaarsen / attention_sinksLinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
☆711Updated 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
- batched loras☆345Updated 2 years ago
- This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and bench…☆594Updated last year
- A bagel, with everything.☆324Updated last year
- ☆538Updated 9 months ago
- ☆416Updated last year
- Generate textbook-quality synthetic LLM pretraining data☆505Updated last year
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆730Updated last year
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆661Updated last year
- ☆547Updated 8 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,598Updated last year
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆959Updated 10 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆425Updated last year
- Official repository for LongChat and LongEval☆530Updated last year
- Tune any FALCON in 4-bit☆466Updated 2 years ago
- The repository for the code of the UltraFastBERT paper☆519Updated last year
- ☆563Updated last year
- [ICLR 2024] Lemur: Open Foundation Models for Language Agents☆556Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆718Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆744Updated 11 months ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆491Updated last year
- Inference code for Persimmon-8B☆415Updated 2 years ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆547Updated last year
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆388Updated last year
- distributed trainer for LLMs☆580Updated last year
- Salesforce open-source LLMs with 8k sequence length.☆722Updated 7 months ago
- Inference code for Mistral and Mixtral hacked up into original Llama implementation☆371Updated last year
- Official repository for ORPO☆465Updated last year
- Train Models Contrastively in Pytorch☆744Updated 5 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,276Updated 6 months ago