There are 3 repositories under cot topic.
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台,我们欢迎开源爱好者发起任何有意义的pr!
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates. - Professor Yu Liu
The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visualization-of-Thought and Chain-of-Thought reasoning to elicit spatial reasoning and perception, emulates, plans and simulates synthetic HID interactions.
Situational Awareness Server compatible with TAK clients
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
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
cot_reports is a Python library for fetching the Commitments of Trader reports of the Commodity Futures Trading Commission (CFTC). The following COT reports are supported: Legacy Futures-only, Legacy Futures-and-Options Combined, Supplemental Futures-and-Options Combined, Disaggregated Futures-only, Disaggregated Futures-and-Options Combined, Traders in Financial Futures (TFF) Futures-only and Traders in Financial Futures (TFF) Futures-and-Options Combined.
Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)
Open Deep Researcher with openai compatible endpoint, now completely local with ollama, local playwright via searxng with citations and planning from CoT
Awesome Reasoning in MLLMs: Papers and Projects about learning to reason with MLLMs, including Chain-of-Thought (CoT), OpenAl o1, and DeepSeek-R1
FreeTAKServer documentation for end users
Research papers about Chain of Thought (CoT)
Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal Large Language Models
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
Python Cursor on Target (CoT) is a Python Module for serializing CoT Events for use with TAK clients & servers
A simple TAK server written in Javascript that relays messages between networks and servers
[arXiv 2501.13117]The Multiplex CoT makes AI more thoughtful.
A no-string API framework for deploying schema-based reasoning into third-party apps
GPT Table Semantic Parsing with complex & non-intuitive structure.
超简单复现Deepseek-R1-Zero和Deepseek-R1,以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL,以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1