modelscope / modelscope-classroom
☆470Updated last week
Related projects ⓘ
Alternatives and complementary repositories for modelscope-classroom
- 通义千问VLLM推理部署DEMO☆437Updated 7 months ago
- Llama3-Tutorial(XTuner、LMDeploy、OpenCompass)☆490Updated 5 months ago
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆231Updated this week
- Chat-甄嬛是利用《甄嬛传》剧本中所有关于甄嬛的台词和语句,基于ChatGLM2进行LoRA微调得到的模仿甄嬛语气的聊天语言模型。☆503Updated 2 months ago
- TinyRAG☆232Updated last week
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆353Updated 6 months ago
- 《大模型白盒子构建指南》:一个全手搓的Tiny-Universe☆1,306Updated last week
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder☆495Updated last week
- Examples and guides for using the GLM APIs☆794Updated 3 weeks ago
- AGI资料汇总学习(主要包括LLM和AIGC),持续更新......☆297Updated last week
- 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
- LLM全栈优质资源汇总☆354Updated last month
- Learning Large Language Model (LLM)(大语言模型学习)☆319Updated 7 months ago
- 心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、InternLM2.5、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3、GLM4、Qwen2、LLama3…☆831Updated 2 weeks ago
- FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目,基于大模型搭建金融场景智能问答系统,利用开源开放来促进「AI+金融」。☆295Updated 4 months ago
- 从零实现一个小参数量中文大语言模型。☆253Updated 2 months ago
- 中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调,给出三元组信息抽取微调示例。☆1,228Updated 6 months ago
- the resources about the application based on LLM with RAG pattern☆844Updated 2 months ago
- 从零实现一个 llama3 中文版☆529Updated 4 months ago
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆320Updated 2 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆144Updated 2 months ago
- Practice to LLM.☆448Updated last week
- CMMLU: Measuring massive multitask language understanding in Chinese☆694Updated this week
- 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
- Netease Youdao's open-source embedding and reranker models for RAG products.☆1,475Updated 2 months ago
- Llama3-Chinese是以Meta-Llama-3-8B为底座,使用 DORA + LORA+ 的训练方法,在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。☆289Updated 6 months ago
- ☆175Updated 7 months ago
- 开源SFT数据集整理,随时补充☆440Updated last year
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆338Updated 11 months ago
- 大语言模型微调,Qwen2、GLM4指令微调☆202Updated 3 months ago