charent / Phi2-mini-ChineseLinks
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.
☆555Updated last year
Alternatives and similar repositories for Phi2-mini-Chinese
Users that are interested in Phi2-mini-Chinese are comparing it to the libraries listed below
Sorting:
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆450Updated 2 months ago
- 中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)☆601Updated last year
- 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。☆1,560Updated last year
- Alpaca Chinese Dataset -- 中文指令微调数据集☆208Updated 9 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆243Updated 10 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☆409Updated last year
- 开源SFT数据集整理,随时补充☆526Updated 2 years ago
- 活字通用大模型☆392Updated 10 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…☆205Updated last year
- 通义千问VLLM推理部署DEMO☆587Updated last year
- Train a 1B LLM with 1T tokens from scratch by personal☆688Updated 2 months ago
- 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)。☆360Updated last year
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆450Updated 3 months ago
- 中文Mixtral-8x7B(Chinese-Mixtral-8x7B)☆650Updated 10 months ago
- chatglm多gpu用deepspeed和☆407Updated last year
- CMMLU: Measuring massive multitask language understanding in Chinese☆772Updated 7 months ago
- ☆343Updated last year
- Awesome Chinese LLM: A curated list of Chinese Large Language Model 中文大语言模型数据集和模型资料汇总☆159Updated last year
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆1,008Updated last year
- 多模态中文LLaMA&Alpaca大语言模型(VisualCLA)☆449Updated last year
- Yuan 2.0 Large Language Model☆688Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆214Updated last year
- Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.☆608Updated 5 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。☆693Updated last month
- 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。☆328Updated 11 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。☆217Updated last year
- 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。☆295Updated last year
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆106Updated last year
- 一些 LLM 方面的从零复现笔记☆205Updated 2 months ago
- 人工精调的中文对话数据集和一段chatglm的微调代码☆1,181Updated 2 months ago