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☆457Updated 2 months ago
- ☆224Updated 4 months ago
- RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models☆489Updated 5 months ago
- ☆205Updated last year
- 使用甄嬛语料微调的chatglm☆84Updated 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 2 weeks ago
- 多轮共情对话模型PICA☆92Updated 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
- Alpaca Chinese Dataset -- 中文指令微调数据集☆193Updated 5 months ago
- deep learning☆150Updated 2 weeks 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…☆98Updated 11 months ago
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆123Updated 2 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.☆249Updated last year
- 从小说中提取对话数据集☆169Updated 9 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆132Updated 3 months ago
- 用于汇总目前的开源中文对话数据集☆143Updated 2 years ago
- Llama2开源模型中文版-全方位测评,基于SuperCLUE的OPEN基准 | Llama2 Chinese evaluation with SuperCLUE☆126Updated last year
- Imitate OpenAI with Local Models☆88Updated 6 months ago
- 我们是第一个完全可商用的角色大模型。☆39Updated 7 months ago
- ☆191Updated 6 months ago
- qwen models finetuning☆93Updated 2 weeks ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆139Updated 11 months ago
- chatglm3base模型的有监督微调SFT☆74Updated last year
- 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
- ☆60Updated last year
- llama inference for tencentpretrain☆98Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆212Updated last year
- chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu☆164Updated last year
- ☆225Updated 10 months ago