glide-the / InterpretationoDreamsLinks
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 month
Alternatives and similar repositories for InterpretationoDreams
Users that are interested in InterpretationoDreams are comparing it to the libraries listed below
Sorting:
- Just for debug☆56Updated last year
- 我们是第一个完全可商用的角色大模型。☆40Updated 10 months ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- Imitate OpenAI with Local Models☆87Updated 9 months ago
- ☆91Updated last year
- A demo built on Megrez-3B-Instruct, integrating a web search tool to enhance the model's question-and-answer capabilities.☆38Updated 6 months ago
- Alpaca Chinese Dataset -- 中文指令微调数据集☆206Updated 8 months ago
- 文本去重☆72Updated last year
- GLM Series Edge Models☆142Updated last week
- the newest version of llama3,source code explained line by line using Chinese☆22Updated 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
- 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☆167Updated 6 months ago
- 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。☆60Updated 5 months ago
- The plan which extend ChatHaruhi into Zero-shot Roleplaying model☆108Updated last year
- A fluent, scalable, and easy-to-use LLM data processing framework.☆21Updated 2 weeks ago
- 探索 LLM 在法律行业的应用潜力☆90Updated 6 months ago
- 🔥Your Daily Dose of AI Research from Hugging Face 🔥 Stay updated with the latest AI breakthroughs! This bot automatically collects and…☆52Updated this week
- ☆66Updated 9 months ago
- Qwen DianJin: LLMs for the Financial Industry by Alibaba Cloud☆109Updated last month
- 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…☆101Updated last year
- 中文原生检索增强生成测评基准☆118Updated last year
- LLM with LuXun (鲁迅) style☆85Updated 2 years ago
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated last year
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆46Updated 5 months ago
- 顾名思义:手搓的RAG☆124Updated last year
- 大语言模型训练和服务调研☆37Updated last year
- qwen models finetuning☆99Updated 3 months ago
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆127Updated 5 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation☆199Updated last week