Stars
Representation Surgery for Multi-Task Model Merging. ICML, 2024.
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Code release for Dataless Knowledge Fusion by Merging Weights of Language Models (https://openreview.net/forum?id=FCnohuR6AnM)
Model Stock: All we need is just a few fine-tuned models
Codebase for Merging Language Models (ICML 2024)
利用HuggingFace的官方下载工具从镜像网站进行高速下载。
Tools for merging pretrained large language models.
Retrieval and Retrieval-augmented LLMs
Is Vec2Text Really a Threat toDense Retrieval Systems?
utilities for decoding deep representations (like sentence embeddings) back to text
Instruct-tune LLaMA on consumer hardware
In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.
本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)
awesome papers in LLM interpretability
[NeurIPS 2024] Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
Data Augmentation for Intent Classification with Off-the-Shelf Large Language Models is a ServiceNow Research project
Official resources of "Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification" (ACL 2023 long).
Code for the KDD-2023 paper: Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler
📋 A list of open LLMs available for commercial use.
Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
An Open-Source Framework for Prompt-Learning.
Pytorch implementation of the paper "Circle Loss: A Unified Perspective of Pair Similarity Optimization"