charent / Phi2-mini-Chinese
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.
☆488Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for Phi2-mini-Chinese
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆353Updated 6 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。☆1,246Updated 7 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☆397Updated last year
- 通义千问VLLM推理部署DEMO☆443Updated 7 months ago
- 开源SFT数据集整理,随时补充☆445Updated last year
- Alpaca Chinese Dataset -- 中文指令微调数据集【人工+GPT4o持续更新】☆185Updated last month
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆329Updated 2 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆319Updated this week
- Baichuan2代码的逐行解析版本,适合小白☆208Updated last year
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.☆511Updated last 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)。☆356Updated last year
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆257Updated this week
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆969Updated 6 months ago
- 从零实现一个小参数量中文大语言模型。☆279Updated 2 months ago
- 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…☆168Updated 6 months ago
- 中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)☆584Updated 6 months ago
- TinyRAG☆235Updated 3 weeks ago
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆395Updated last year
- ☆213Updated 6 months ago
- 中文Mixtral-8x7B(Chinese-Mixtral-8x7B)☆641Updated 3 months ago
- ☆266Updated 5 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
- 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。☆476Updated 6 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆152Updated 2 months ago
- 活字通用大模型☆353Updated 2 months ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆332Updated 3 months ago
- 雅意信息抽取大模型:在百万级人工构造的高质量信息抽取数据上进行指令微调,由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆270Updated 3 months ago
- Llama3-Tutorial(XTuner、LMDeploy、OpenCompass)☆492Updated 6 months ago
- 本地知识库 + chatGLM6B + CustomAgent☆262Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Updated last year