zhaibowen / Retriever
Retriever-0.1B
☆70Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for Retriever
- 通义千问VLLM推理部署DEMO☆438Updated 7 months ago
- 尝试自己从头写一个LLM,参考llama和nanogpt☆38Updated 6 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆145Updated 2 months ago
- 从零实现一个小参数量中文大语言模型。☆257Updated 2 months ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆353Updated 6 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.☆483Updated 4 months ago
- Alpaca Chinese Dataset -- 中文指令微调数据集【人工+GPT4o持续更新】☆184Updated last month
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆322Updated 2 months ago
- TinyRAG☆233Updated 2 weeks ago
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆236Updated this week
- 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)。☆355Updated last year
- 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」。☆296Updated 5 months ago
- 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
- Huggingface transformers的中文文档☆172Updated last year
- Train a Chinese LLM From 0 by Personal☆201Updated last week
- Tutorial on training, evaluating LLM, as well as utilizing RAG, Agent, Chain to build entertaining applications with LLMs.分享如何训练、评 估LLMs,如…☆518Updated 6 months ago
- qwen ai agent☆109Updated 8 months ago
- personal chatgpt☆317Updated this week
- chatglm3base模型的有监督微调SFT☆74Updated last year
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆266Updated 3 months ago
- 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。☆202Updated 11 months ago
- 基于BM25、BGE的检索增强生成RAG示例☆97Updated 2 weeks ago
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder☆501Updated this week
- 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。☆1,235Updated 6 months ago
- ☆81Updated this week
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆166Updated 5 months ago
- 使用单个24G显卡,从0开始训练LLM☆49Updated 2 weeks ago
- chatglm多gpu用deepspeed和☆402Updated 4 months ago
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆340Updated 11 months ago
- 中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)☆582Updated 6 months ago