rangwang / CCAC2024-FS_ModerationLinks
CCAC2024——大模型安全的双重防线:少样本文本内容安全挑战赛仓库
☆26Updated last year
Alternatives and similar repositories for CCAC2024-FS_Moderation
Users that are interested in CCAC2024-FS_Moderation are comparing it to the libraries listed below
Sorting:
- SC-Safety: 中文大模型多轮对抗安全基准☆137Updated last year
- 大模型文本分类☆65Updated 10 months ago
- The official repository of the paper: COLD: A Benchmark for Chinese Offensive Language Detection☆273Updated 2 years ago
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆225Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆67Updated last year
- The code and resource of "Towards Comprehensive Detection of Chinese Harmful Memes" (NeurIPS2024 D&B).☆45Updated last month
- 大语言模型应用:RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆62Updated 4 months ago
- A Survey of LLM Alignment (SFT & RLHF), and A Survey of RLHF methods (2023~2024)☆18Updated last year
- The code and resource of "Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmark"…☆77Updated last month
- 一套代码指令微调大模型☆39Updated last year
- 基于ChatGPT构建的中文self-instruct数据集☆118Updated 2 years ago
- LLM for NER☆73Updated 10 months ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆80Updated 11 months ago
- 对llama3进行全参微调、lora微调以及qlora微调。☆199Updated 8 months ago
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆198Updated 8 months ago
- 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
- 怎么训练一个LLM分词器☆150Updated last year
- text security audit 安全审核-语义模型过滤 敏感内容检测系统☆25Updated 4 months ago
- deepspeed+trainer简单高效实现多卡微调大模型☆126Updated 2 years ago
- 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☆86Updated 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。☆118Updated 3 months ago
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆102Updated last year
- 多轮共情对话模型PICA☆94Updated last year
- 大模型检索增强生成技术最佳实践。☆79Updated 9 months ago
- 使用LoRA对Chinese-LLaMA-Alpaca进行微调。☆34Updated 2 years ago
- 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☆15Updated 2 years ago
- ☆111Updated 11 months ago
- 文本相似度,语义向量,文本向量,text-similarity,similarity, sentence-similarity,BERT,SimCSE,BERT-Whitening,Sentence-BERT, PromCSE, SBERT☆74Updated 7 months ago
- 基于qlora对baichuan-7B大模型进行指令微调。☆23Updated 2 years ago
- 本文提出了一个基于“文心一言”的中国LLMs的安全评估基准,其中包括8种典型的安全场景和6种指令攻击类型。此外,本文还提出了安全评估的框架和过程,利用手动编写和收集开源数据的测试Prompts,以及人工干预结合利用LLM强大的评估能力作为“共同评估者”。☆25Updated last year