SmartFlowAI / Llama3-Tutorial
Llama3-Tutorial(XTuner、LMDeploy、OpenCompass)
☆506Updated 10 months ago
Alternatives and similar repositories for Llama3-Tutorial:
Users that are interested in Llama3-Tutorial are comparing it to the libraries listed below
- AGI资料汇总学习(主要包括LLM和AIGC),持续更新......☆344Updated 2 months ago
- 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。☆628Updated 6 months ago
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆395Updated 6 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆223Updated 6 months ago
- ☆793Updated this week
- TinyRAG☆275Updated 4 months ago
- 从零实现一个 llama3 中文版☆708Updated 9 months ago
- 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.☆537Updated 8 months 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」。☆355Updated 9 months ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆409Updated 10 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆576Updated last week
- 通义千问VLLM推理部署DEMO☆546Updated 11 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。☆294Updated 10 months ago
- 基于ReAct手搓一个Agent Demo☆117Updated 10 months ago
- ☆85Updated 2 weeks 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。☆1,468Updated 11 months ago
- 顾名思义:手搓的RAG☆121Updated last year
- 从零实现一个小参数量中文大语言模型。☆553Updated 7 months ago
- 企业级RAG系统从入门到精通☆382Updated last week
- 大语言模型微调,Qwen2VL、Qwen2、GLM4指令微调☆338Updated last month
- 从小说中提取对话数据集☆169Updated 9 months ago
- An easy-to-use framework for modular RAG☆340Updated this week
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆989Updated 10 months ago
- 开源SFT数据集整理,随时补充☆500Updated last year
- LLM全栈优质资源汇总☆505Updated 3 months ago
- Examples and guides for using the GLM APIs☆856Updated last month
- 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…☆1,303Updated last month
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆354Updated 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.☆229Updated 3 months ago