LongAlign

Long Context Aligner

A framework for training and evaluating large language models on long context inputs

[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs

GitHub

230 stars
8 watching
15 forks
Language: Python
last commit: 2 months ago
alignmentllmlong-contextlongtext

Related projects:

Repository Description Stars
evolvinglmms-lab/longva An open-source project that enables the transfer of language understanding to vision capabilities through long context processing. 347
academic-hammer/hammerllm A large language model pre-trained on Chinese and English data, suitable for natural language processing tasks. 43
luogen1996/lavin An open-source implementation of a vision-language instructed large language model 513
thudm/agentbench A benchmark suite for evaluating the ability of large language models to operate as autonomous agents in various environments 2,272
zhoux85/staligner Tool for aligning and integrating spatially resolved transcriptomics data using machine learning algorithms 29
deeplangai/lingowhale-8b An open bilingual LLM developed using the LingoWhale model, trained on a large dataset of high-quality middle English text, and fine-tuned for specific tasks such as conversation generation. 134
damo-nlp-sg/m3exam A benchmark for evaluating large language models in multiple languages and formats 93
thudm/chinese-transformer-xl A pre-trained Chinese language model based on the Transformer-XL architecture. 218
tanloong/interlaced.nvim A plugin for aligning bilingual parallel texts by re-positioning text and applying highlighting. 7
boheumd/ma-lmm This project develops an AI model for long-term video understanding 254
machinalis/yalign Automates the process of extracting parallel sentences from comparable corpora to aid in statistical machine translation 127
talschuster/crosslingualcontextualemb Enables alignment of word embeddings across multiple languages to facilitate cross-lingual text analysis and machine learning tasks 99
pku-alignment/align-anything Aligns large multimodal models with human intentions and values using various algorithms and fine-tuning methods. 270
victordibia/llmx An API that provides a unified interface to multiple large language models for chat fine-tuning 79
qcri/llmebench A benchmarking framework for large language models 81