abacusai / Long-ContextLinks
This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and benchmark tasks that evaluate a model’s information retrieval capabilities with context expansion. We also include key experimental results and instructions for reproducing and building on them.
☆589Updated last year
Alternatives and similar repositories for Long-Context
Users that are interested in Long-Context are comparing it to the libraries listed below
Sorting:
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆699Updated last year
- Code for fine-tuning Platypus fam LLMs using LoRA☆629Updated last year
- Generate textbook-quality synthetic LLM pretraining data☆500Updated last year
- Official repository for LongChat and LongEval☆521Updated last year
- [ICLR 2024] Lemur: Open Foundation Models for Language Agents☆550Updated last year
- OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA☆302Updated 2 years ago
- Inference code for Mistral and Mixtral hacked up into original Llama implementation☆371Updated last year
- NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRav…☆315Updated last year
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆948Updated 8 months ago
- ☆415Updated last year
- LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions☆819Updated 2 years ago
- ☆270Updated 2 years ago
- Salesforce open-source LLMs with 8k sequence length.☆717Updated 5 months ago
- ☆520Updated 7 months ago
- Build, evaluate, understand, and fix LLM-based apps☆489Updated last year
- A joint community effort to create one central leaderboard for LLMs.☆300Updated 10 months ago
- Official codebase for "SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation"☆227Updated 2 years ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆222Updated last year
- This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious c…☆222Updated 2 years ago
- ☆1,030Updated 2 years ago
- A tiny library for coding with large language models.☆1,232Updated 11 months ago
- batched loras☆342Updated last year
- Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".☆801Updated last year
- PaL: Program-Aided Language Models (ICML 2023)☆501Updated 2 years ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,501Updated last year
- data cleaning and curation for unstructured text☆327Updated 10 months ago
- A bagel, with everything.☆322Updated last year
- ☆543Updated 10 months ago
- LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transform…☆1,458Updated last year
- Fine-Tuning Embedding for RAG with Synthetic Data☆502Updated last year