LC1332 / Zero-Haruhi
The plan which extend ChatHaruhi into Zero-shot Roleplaying model
☆104Updated 11 months ago
Alternatives and similar repositories for Zero-Haruhi:
Users that are interested in Zero-Haruhi are comparing it to the libraries listed below
- Just for debug☆56Updated last year
- [EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models☆453Updated 2 months ago
- ☆223Updated 3 months ago
- RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models☆487Updated 5 months ago
- 基于《西游记》原文、白话文、ChatGPT生成数据制作的,以InternLM2微调的角色扮演多LLM聊天室。 本项目将介绍关于角色扮演类 LLM 的一切,从数据获取、数据处理,到使用 XTuner 微调并部署至 OpenXLab,再到使用 LMDeploy 部署,以 op…☆96Updated 11 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 this week
- 使用甄嬛语料微调的chatglm☆84Updated last year
- 从小说中提取对话数据集☆163Updated 8 months ago
- ☆189Updated 5 months ago
- 我们是第一个完全可商用的角色大模型。☆39Updated 7 months ago
- ☆202Updated last year
- Psychological Counselor's Digital Twin Framework(心理咨询师数字孪生框架)☆111Updated 2 months ago
- A Multi-modal RAG Project with Dataset from Honor of Kings, one of the most popular smart phone games in China☆63Updated 6 months ago
- 用于汇总目前的开源中文对话数据集☆140Updated 2 years ago
- deep learning☆150Updated this week
- ☆60Updated last year
- Alpaca Chinese Dataset -- 中文指令微调数据集☆193Updated 5 months ago
- 用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.☆248Updated last year
- 文本语料转训练集工具,txt转dataset☆89Updated 10 months ago
- Imitate OpenAI with Local Models☆87Updated 6 months ago
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆122Updated 2 months ago
- 骆驼QA,中文大语言阅读理解模型。☆75Updated last year
- 多轮共情对话模型PICA☆92Updated last year
- GLM Series Edge Models☆130Updated 3 weeks ago
- 😜 表情包视觉数据集,使用glm-4v、step-1v的图像解析能力标注。☆115Updated 10 months ago
- 骆驼大乱斗: Massive Game Content Generated by LLM☆19Updated last year
- SUS-Chat: Instruction tuning done right☆48Updated 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 6 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)☆89Updated last year
- ☆51Updated 7 months ago