yangjianxin1 / unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
☆28Updated 11 months ago
Alternatives and similar repositories for unsloth:
Users that are interested in unsloth 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
- 最简易的R1结果在小模型上的复现,阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证,对于强推理能力,think思考过程性内容是AGI/ASI的核心。☆43Updated 2 months ago
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆22Updated 9 months ago
- ☆26Updated 6 months ago
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆37Updated 11 months ago
- 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
- zero零训练llm调参☆31Updated last year
- 百度QA100万数据集☆47Updated last year
- 想要从零开始训练一个中文的mini大语言模型,可以进行基本的对话,模型大小根据手头的机器决定☆59Updated 8 months ago
- 纯c++的全平台llm加速库,支持python调用,支持baichuan, glm, llama, moss基座,手机端流畅运行chatglm-6B级模型单卡可达10000+token / s,☆45Updated last year
- GPT+神器,简单实用的一站式AGI架构,内置本地化,LLM模型,agent,矢量数据库,智能链chain☆48Updated last year
- XVERSE-7B: A multilingual large language model developed by XVERSE Technology Inc.☆52Updated last year
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆57Updated 5 months ago
- GLM Series Edge Models☆136Updated 2 months ago
- Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理,可实现 CPU 上毫秒级的 OCR 精准预测,通用场景中英文OCR达到开源SO…☆73Updated 2 months ago
- 全球首个StableVicuna中文优化版。☆64Updated last year
- 实现Blip2RWKV+QFormer的多模态图文对话大模型,使用Two-Step Cognitive Psychology Prompt方法,仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4,ImageBind等图文对话大语言模型,力求以更小的算力和资源实…☆38Updated last year
- 我们是第一个完全可商用的角色大模型。☆39Updated 8 months ago
- the newest version of llama3,source code explained line by line using Chinese☆22Updated last year
- Imitate OpenAI with Local Models☆88Updated 7 months ago
- Its an open source LLM based on MOE Structure.☆58Updated 9 months ago
- A light proxy solution for HuggingFace hub.☆46Updated last year
- (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
- ☆16Updated 10 months ago
- TPO 是一个优化 LLM 输出文本的框架,通过迭代反馈和优化提示的方式来“微调模型”,而非直接调整模型的参数,使模型在推理过程中与人类偏好对齐以生成更好的结果。本项目提供了一个友好的 WebUI 来加载模型,实时优化基础模型并展示最佳结果。☆10Updated last month
- SUS-Chat: Instruction tuning done right☆48Updated last year
- 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
- 千问14B和7B的逐行解释☆57Updated last year
- 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
- A Toolkit for Running On-device Large Language Models (LLMs) in APP☆72Updated 9 months ago