epfml / landmark-attentionLinks
Landmark Attention: Random-Access Infinite Context Length for Transformers
☆423Updated last year
Alternatives and similar repositories for landmark-attention
Users that are interested in landmark-attention are comparing it to the libraries listed below
Sorting:
- A bagel, with everything.☆323Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆199Updated 11 months ago
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆388Updated last year
- Merge Transformers language models by use of gradient parameters.☆206Updated 11 months ago
- ☆416Updated last year
- Official repository for LongChat and LongEval☆524Updated last year
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆659Updated last year
- ☆95Updated 2 years ago
- batched loras☆344Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆459Updated last year
- ☆546Updated 7 months ago
- ☆458Updated last year
- ☆270Updated 2 years ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆702Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆697Updated 11 months ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆223Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆376Updated last year
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆546Updated last year
- ☆535Updated last year
- Pre-training code for Amber 7B LLM☆167Updated last year
- ☆366Updated 2 years ago
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"☆306Updated last year
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆205Updated last year
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆200Updated 2 years ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- Inference code for Mistral and Mixtral hacked up into original Llama implementation☆371Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆239Updated last year
- Inference code for Persimmon-8B☆415Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆509Updated last year