thu-coai / Safety-Prompts
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
☆867Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for Safety-Prompts
- 面向中文大模型价值观的评估与对齐研究☆473Updated last year
- 开源SFT数据集整理,随时补充☆440Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆654Updated last year
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆154Updated 4 months ago
- CMMLU: Measuring massive multitask language understanding in Chinese☆696Updated this week
- "他山之石、可以攻玉":复旦白泽智能发布面向国内开源和 国外商用大模型的Demo数据集JADE-DB☆311Updated 4 months ago
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆967Updated 6 months ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆330Updated 2 months ago
- 人工精调的中文对话数据集和一段chatglm的微调代码☆1,155Updated 6 months ago
- ☆490Updated 5 months ago
- GAOKAO-Bench is an evaluation framework that utilizes GAOKAO questions as a dataset to evaluate large language models.☆546Updated 7 months ago
- FlagEval is an evaluation toolkit for AI large foundation models.☆299Updated 3 months ago
- Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]☆1,633Updated last year
- SC-Safety: 中文大模型多轮对抗安全基准☆105Updated 7 months ago
- 语言模型中文认知能力分析☆235Updated last year
- Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆396Updated last year
- 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)。☆354Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆467Updated 2 years ago
- unified embedding model☆828Updated last year
- Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型,支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.☆482Updated 3 months ago
- Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs…☆429Updated 2 weeks ago
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆234Updated last year
- 活字通用大模型☆351Updated last month
- ☆887Updated 5 months ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆353Updated 6 months ago
- 本项目旨在收集开源的表格智能任务数据集(比如表格问答、表格-文本生成等),将原始数据整理为指令微调格式的数据并微调LLM,进而增强LLM对于表格数据的理解,最终构建出专门面向表格智能任务的大型语言模型。☆463Updated 6 months ago
- chatglm多gpu用deepspeed和☆402Updated 4 months ago
- Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.☆575Updated 4 months ago
- LLMs interview notes and answers:该仓库主要记录大模型(LLMs)算法工程师相关的面试题和参考答案☆1,162Updated 10 months ago
- ☆263Updated 4 months ago