CrazyBoyM / LLM-Chinese
(撰写ing..)本仓库偏教程性质,以「模型中文化」为一个典型的模型训练问题切入场景,指导读者上手学习LLM二次微调训练。
☆33Updated 8 months ago
Alternatives and similar repositories for LLM-Chinese:
Users that are interested in LLM-Chinese are comparing it to the libraries listed below
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆37Updated 4 months ago
- 大语言模型训练和服务调研☆37Updated last year
- This repository provides an implementation of the paper "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Co…☆66Updated last month
- the newest version of llama3,source code explained line by line using Chinese☆22Updated 11 months ago
- 中文原生检索增强生成测评基准☆115Updated last year
- ☆63Updated 7 months ago
- 中文基于满血DeepSeek-R1蒸馏数据集☆55Updated last month
- 用于微调LLM的中文指令数据集☆26Updated 2 years ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- 文本去重☆70Updated 10 months ago
- ☆225Updated 11 months ago
- Imitate OpenAI with Local Models☆88Updated 7 months ago
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆45Updated 3 months ago
- ☆90Updated last year
- Alpaca Chinese Dataset -- 中文指令微调数据集☆195Updated 6 months ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆139Updated last year
- 顾名思义:手搓的RAG☆121Updated last year
- 本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作☆61Updated 5 months ago
- 使用langchain进行任务规划,构建子任务的会话场景资源,通过MCTS任务执行器,来让每个子任务通过在上下文中资源,通过自身反思探索来获取自身对问题的最优答案;这种方式依赖模型的对齐偏好,我们在每种偏好上设计了一个工程框架,来完成自我对不同答案的奖励进行采样策略☆29Updated last week
- 我们是第一个完全可商用的角色大模型。☆39Updated 8 months ago
- SuperCLUE琅琊榜:中文通用大模型匿名对战评价基准☆145Updated 9 months ago
- 本项目致力于为大模型领域的初学者提供全面的知识体系,包括基础和高阶内容,以便开发者能迅速掌握大模型技术栈并全面了解相关知识。☆55Updated 3 months ago
- ☆139Updated 10 months ago
- Light local website for displaying performances from different chat models.☆86Updated last year
- (1)弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练,提高万级tokens性能支持。(2)证据理论解释学习,提升模型的复杂逻辑推理能力(3)兼容alpaca数据格式。☆44Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆107Updated last year
- qwen models finetuning☆97Updated last month
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated last year
- 首个llama2 13b 中文版模型 (Base + 中文对话SFT,实现流畅多轮人机自然语言交互)☆90Updated last year