morning-hao / domain-self-instruct
受到self-instruct启发,除了通用LLM还能做垂直领域的小LLM实现定制效果,通过GPT获得question和answer来作为训练数据
☆14Updated last year
Alternatives and similar repositories for domain-self-instruct:
Users that are interested in domain-self-instruct are comparing it to the libraries listed below
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆75Updated 4 months ago
- 本项目用于Embedding模型的相关实验,包括Embedding模型评估、Embedding模型微调、Embedding模型量化等。☆44Updated 7 months ago
- ☆133Updated 10 months ago
- baichuan LLM surpervised finetune by lora☆62Updated last year
- ☆104Updated 8 months ago
- basic framework for rag(retrieval augment generation)☆82Updated last year
- 专注于中文领域大语言模型,落地到某个行业某个领域,成为一个行业大模型、公司级别或行业级别领域大模型。☆116Updated last week
- RAG 论文学习☆69Updated last month
- Baichuan-13B 指令微调☆89Updated last year
- text embedding☆145Updated last year
- ChatGLM-6B添加了RLHF的实现,以及部分核心代码的逐行讲 解 ,实例部分是做了个新闻短标题的生成,以及指定context推荐的RLHF的实现☆82Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆171Updated last year
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答 baseline 80+☆91Updated last year
- 本项目使用大语言模型(LLM)进行开放领域三元组抽取。☆26Updated last year
- ☆64Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆106Updated last year
- LLM for NER☆66Updated 7 months ago
- 中文 Instruction tuning datasets☆128Updated 11 months ago
- ☆160Updated last year
- 本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.☆223Updated 2 months ago
- 快速入门RAG与私有化部署☆156Updated 10 months ago
- Viscacha:通用信息抽取数据集收集☆26Updated last year
- llama,chatglm 等模型的微调☆86Updated 7 months ago
- 怎么训练一个LLM分词器☆142Updated last year
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测,低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆213Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆344Updated 6 months ago
- [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus☆188Updated 2 months ago
- A collection for math word problem (MWP) works, including datasets, algorithms and so on.☆42Updated 8 months ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆78Updated 8 months ago
- ☆165Updated last year