xiwan / LLM-Game-AgentsLinks
This is a repo for studying the application of LLM Agents on Games
☆65Updated last month
Alternatives and similar repositories for LLM-Game-Agents
Users that are interested in LLM-Game-Agents are comparing it to the libraries listed below
Sorting:
- The Silk Magic Book will record the Magic Prompts on some very Large LLMs. The Silk Magic Book belongs to the project Luotuo(骆驼), which c…☆56Updated 2 years ago
- A Game Demo Powered by ChatGPT Agents☆270Updated last year
- The plan which extend ChatHaruhi into Zero-shot Roleplaying model☆108Updated 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
- 李鲁鲁老师对 吴恩达《ChatGPT Prompt Engineering for Developers》课程中文版的实践☆135Updated last year
- 斯坦福工作 Generative Agents的复现和翻译 An attempt to build a working, locally-running cheap version of Generative Agents: Interactive Simulacra of…☆84Updated 2 years ago
- Perform crosstalk with Qian Yu☆54Updated last year
- ☆151Updated last year
- Easy, fast, and cheap pretrain,finetune, serving for everyone☆310Updated last month
- A simulation of world using GPTs. (depreciated)☆157Updated last year
- Just for debug☆56Updated last year
- [EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models☆468Updated 6 months ago
- A small open source 3D agent simulator based on LLM.☆66Updated 7 months ago
- 骆驼大乱斗: Massive Game Content Generated by LLM☆19Updated last year
- 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
- 2024 Alibaba Global Mathematics Competition AI Track Global 2nd Place Project (Agent Universe)☆70Updated last year
- SuperCLUE琅琊榜：中文通用大模型匿名对战评价基准☆145Updated last year
- 我们是第一个完全可商用的角色大模型。☆40Updated 11 months ago
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆28Updated last year
- mem1是mem0的魔改版本。我的魔改能让它生成效果更可用和更适合做情感陪伴项目☆26Updated 7 months ago
- 利用LLM+敏感词库，来自动判别是否涉及敏感词。☆126Updated 2 years ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆139Updated last year
- Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。☆295Updated last year
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆129Updated 6 months ago
- ☆66Updated 8 months ago
- ☆270Updated 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 this week
- 中文基于满血DeepSeek-R1蒸馏数据集☆56Updated 4 months ago
- ☆105Updated last year
- 从头开始训练一个chatglm小模型☆46Updated last year