ClosedCharacter / Peach
我们是第一个完全可商用的角色大模型。
☆39Updated 8 months ago
Alternatives and similar repositories for Peach:
Users that are interested in Peach are comparing it to the libraries listed below
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆68Updated last year
- GLM Series Edge Models☆136Updated 2 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
- 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
- 😜 表情包视觉数据集,使用glm-4v、step-1v的图像解析能力标注。☆119Updated 11 months ago
- 🔥Your Daily Dose of AI Research from Hugging Face 🔥 Stay updated with the latest AI breakthroughs! This bot automatically collects and…☆50Updated this week
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆22Updated 9 months ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- Deep Reasoning Translation via Reinforcement Learning (arXiv preprint 2025); DRT: Deep Reasoning Translation via Long Chain-of-Thought (a…☆215Updated last week
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆125Updated 3 months ago
- Evaluation for AI apps and agent☆40Updated last year
- Its an open source LLM based on MOE Structure.☆58Updated 9 months ago
- ☆226Updated 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
- Imitate OpenAI with Local Models☆88Updated 7 months ago
- ☆36Updated 6 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
- 利用免费的大模型api来结合你的私域数据来生成sft训练数据(妥妥白嫖)支持llamafactory等工具的训练数据格式synthetic data☆155Updated 5 months ago
- (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
- ☆78Updated 11 months ago
- A lightweight script for processing HTML page to markdown format with support for code blocks☆79Updated last year
- 基于baichuan-7b的开源多模态大语言模型☆73Updated last year
- SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama: https://arxiv.org/abs/2408.09333v2☆119Updated 5 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆131Updated 10 months ago
- Just for debug☆56Updated last year
- 顾名思义:手搓的RAG☆121Updated last year
- zero零训练llm调参☆31Updated last year
- A Python Package to Access World-Class Generative Models☆128Updated 10 months ago
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆37Updated 11 months ago
- Using APPL to reimplement popular algorithms for Large Language Models (LLMs) and prompts☆44Updated 3 months ago