Pinned Repositories
AiMed
AiMed面向中文医学的人工智能大语言模型期望实现有效处理医学知识问答、医学论文阅读、医学文献检索等任务和在医学科研中的应用。
Med-Eval
Med-Eval 是一个全球性、多维度的医学大语言模型测评基准,旨在推动医学领域的技术进步和人类医学的发展,以满足不断增长的信息处理和医疗需求。它试图为医学大模型的研究、应用和创新提供资源和指导。
RAG-NEWS
本项目实现了一个简单的 RAG 框架,并使 LLM 能够获取有关 2023 年新闻的信息。
BDAP_MultimodalDialogueScenariosAndTopicSwitchingUnderstanding
给定视频和对话,利用深度学习相关技术,建立稳健的对话场景切换和对话话题切换判断模型。
CL_NLP_CCPM-CMeEE
MedRad
A Framework for Reliable Assisted Decision Making in a Medical Large Model
WindPro2.0
风力发电气动平衡监测系统2.0
AI_MachineTranslation
人工智能原理-机器翻译项目
alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
BDA_HandwrittenCharacterRecognition
dujh22's Repositories
dujh22/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
dujh22/Crime-Prediction-Model
Establishment and optimization of crime prediction models
dujh22/prm800k
800,000 step-level correctness labels on LLM solutions to MATH problems
dujh22/math-feedback
High-Performance Algorithms Significantly Improve LLM's Mathematical Reasoning Ability
dujh22/GSM8K
Dataset used to test LLM math skills
dujh22/llm-learning
本项目旨在分享大模型相关技术原理以及实战经验。
dujh22/mistral-7b
Reference implementation of Mistral AI 7B v0.1 model.
dujh22/llama3
The official Meta Llama 3 GitHub site
dujh22/llm-learning2
《动手学大模型Dive into LLMs》系列编程实践教程
dujh22/MedRad
A Framework for Reliable Assisted Decision Making in a Medical Large Model
dujh22/AiMed
AiMed面向中文医学的人工智能大语言模型期望实现有效处理医学知识问答、医学论文阅读、医学文献检索等任务和在医学科研中的应用。
dujh22/Med-Eval
Med-Eval 是一个全球性、多维度的医学大语言模型测评基准,旨在推动医学领域的技术进步和人类医学的发展,以满足不断增长的信息处理和医疗需求。它试图为医学大模型的研究、应用和创新提供资源和指导。
dujh22/ChatGLM-MathV2.1
This project accomplishes an automated preparation process for datasets used to enhance the mathematical capabilities of large models through an exhaustive pipeline design.
dujh22/ChatGLM-MathV2
chatglm math reasoning
dujh22/Med-Eval-Arena
dujh22/ChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
dujh22/alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
dujh22/BDAP_PersonalizedRecommendation
大数据分析与处理-个性化推荐
dujh22/x-LLM
dujh22/math
The MATH Dataset (NeurIPS 2021)
dujh22/KE_Knowledge-oriented_reading_comprehension
面向知识的阅读理解
dujh22/MMLU
Measuring Massive Multitask Language Understanding | ICLR 2021
dujh22/CEMS
Solving the problem of mixing Chinese and English in model responses
dujh22/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
dujh22/CEMS-Dataset
Construction of Chinese-English mixed task dataset
dujh22/ChatGLM-Math
Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
dujh22/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
dujh22/Dujinhua_wiki
Dujinhua's personal wiki information
dujh22/RAG-NEWS
本项目实现了一个简单的 RAG 框架,并使 LLM 能够获取有关 2023 年新闻的信息。
dujh22/dujh22.github.io