Code and Benchmark Dataset for DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

[NeurIPS'24 Oral] HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning

CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks

Code for the MedRAG toolkit

Robust recipes to align language models with human and AI preferences

[𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯𝘨 𝘪𝘯 𝘓𝘢𝘯𝘨𝘶𝘢𝘨𝘦 𝘔𝘰𝘥𝘦𝘭𝘴 𝘸𝘪𝘵𝘩 𝘍𝘪𝘯𝘦-𝘨𝘳𝘢𝘪𝘯𝘦𝘥 𝘙𝘦𝘸𝘢𝘳𝘥𝘴

Repository for the code to the paper "A Dataset for Plain Language Adaptation of Biomedical Abstracts"

最好用的 V2Ray 一键安装脚本 & 管理脚本

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

A framework for few-shot evaluation of language models.

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

Small and Efficient Mathematical Reasoning LLMs

Code for Quiet-STaR

[MathCoder, MathCoder-VL] Family of LLMs/LMMs for mathematical reasoning.

The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Google Research

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

北京大学软件与微电子学院硕士生课程知识点、作业等汇总【Summary of Knowledge Points and Assignments of Peking University Integrated Circuit Major Courses】

A professional list on Large (Language) Models and Foundation Models (LLM, LM, FM) for Time Series, Spatiotemporal, and Event Data.

Awesome-LLM: a curated list of Large Language Model

A collection of AWESOME things about domain adaptation

A benchmark for few-shot evaluation of foundation models for electronic health records (EHRs)

Code for "DistCare: Distilling Knowledge from Publicly Available Online EMR Data to Emerging Epidemic for Prognosis" (WWW '21)