Pinned Repositories
2018-CCF-BDCI-China-Unicom-Research-Institute-top2
2018-CCF大数据与计算智能大赛-面向电信行业存量用户的智能套餐个性化匹配模型联通赛-复赛第二名
2018-iFLYTEK-Marketing-Algorithms-Competition-Finals-Rank1
2018科大讯飞营销算法大赛（冠军方案）
2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement
2019CCF-BDCI大赛 最佳创新探索奖获得者 基于OCR身份证要素提取赛题冠军 天晨破晓团队 赛题源码
2019Baai-zhihu-Cup-findexp-4th
2019年知乎看山杯第四名
Chatbot_CN
基于金融-司法领域(兼有闲聊性质)的聊天机器人，其中的主要模块有信息抽取、NLU、NLG、知识图谱等，并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口
CrossWOZ
A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
DIAC
问题等价性判断数据预处理，包含添加对抗样本（同音字、近义词替换等）、获取样本的pattern（用通配符替换相同词汇，提取相同和不同词汇）
DrQA
Reading Wikipedia to Answer Open-Domain Questions
lmft
Language Model Fine-Tuning, for ChatGLM, BELLE, LLaMA fine-tuning.
MacBERT
Revisiting Pre-trained Models for Chinese Natural Language Processing (Findings of EMNLP)
haojiepan1's Repositories
haojiepan1/AutoGPT
An experimental open-source attempt to make GPT-4 fully autonomous.
haojiepan1/Baichuan-13B
A 13B large language model developed by Baichuan Intelligent Technology
haojiepan1/blade-build
Blade is a powerful build system from Tencent, supports many mainstream programming languages, such as C/C++, java, scala, python, protobuf...
haojiepan1/chatGLM-6B-QLoRA
使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。
haojiepan1/ChatGLM-Efficient-Tuning
Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
haojiepan1/chatgpt-corpus
ChatGPT 中文语料库 对话语料 小说语料 客服语料
haojiepan1/ChatPaper
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
haojiepan1/ChuanhuChatGPT
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
haojiepan1/DecryptPrompt
总结Prompt&LLM论文，开源数据&模型，AIGC应用
haojiepan1/docker-llama2-chat
Play LLaMA2 (official / 中文版 / INT4 / llama2.cpp) Together! ONLY 3 STEPS! ( non GPU / 5GB vRAM / 8~14GB vRAM)
haojiepan1/FinanceChatGLM
SMP 2023 ChatGLM金融大模型挑战赛 60 分baseline思路介绍
haojiepan1/FinGLM
haojiepan1/hcgf
Humanable ChatGLM/GPT Fine-tuning | ChatGLM微调
haojiepan1/Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain
haojiepan1/LLaMA-Efficient-Tuning
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
haojiepan1/LLM4Science
kaggle LLM contest Silver solution
haojiepan1/LLMZoo
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡
haojiepan1/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
haojiepan1/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练、有监督微调、RLHF(奖励建模、强化学习训练)和DPO(直接偏好优化)。
haojiepan1/NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
haojiepan1/openai-cookbook
Examples and guides for using the OpenAI API
haojiepan1/openai-python
The official Python library for the OpenAI API
haojiepan1/pandallm
Panda项目是于2023年5月启动的开源海外中文大语言模型项目，致力于大模型时代探索整个技术栈，旨在推动中文自然语言处理领域的创新和合作。
haojiepan1/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
haojiepan1/RQ-RAG
haojiepan1/textgen
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型，实现了包括LLaMA，ChatGLM，BLOOM，GPT2，Seq2Seq，BART，T5，UDA等模型的训练和预测，开箱即用。
haojiepan1/uie_pytorch
PaddleNLP UIE模型的PyTorch版实现
haojiepan1/uniem
unified embedding model
haojiepan1/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
haojiepan1/WSDM-Cup-2024
1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc