Awesome LLM Papers and repos on very comprehensive topics.

gpt-o1 like chain of thoughts with local LLMs in R

Arcmind Autonomous AI Agent powered by Dfinity's Internet Computer

The official fork of THoR Chain-of-Thought framework, enhanced and adapted for Emotion Cause Analysis (ECAC-2024)

The official code for CoT / ZSL reasoning framework 🧠, utilized in paper: "Large Language Models in Targeted Sentiment Analysis in Russian"

GPT natural-language user interface that fakes emotions and plans actions

A collection of prompts and techniques to enhance the reasoning, response development, and quality of Large Language Models (LLMs).

This project explores GPT-2 and Llama models through pre-training, fine-tuning, and Chain-of-Thought (CoT) prompting. It includes memory-efficient optimizations (SGD, LoRA, BAdam) and evaluations on math datasets (GSM8K, NumGLUE, StimulEq, SVAMP).

OmniLlama é minha tentativa de criar uma maneira eficiente, local de trabalhar com cadeias de raciocínio com modelos relativamente pequenos.

This repository is a proof of concept for replicating the reasoning capabilities of OpenAI's O1 model using alternative frameworks. It employs a sequential agent-based system powered by the Gemini API, facilitating iterative problem-solving for coding-related challenges through a Flask web application.

combating the llm fomo, feeding the shiny object syndrome, for folly and partially for curiousity

ragTAG is a conversational AI script that creates a roundtable dialogue between user assigned characters with their own different objectives and perspectives.

LLM model that aims to accurately solve calculations from expressions and word problems

This is the repo for Vicuna Chemical Expert, which can help to solve some chemical questions.

按照CoT原理设计的AI工作流，可配置、可中断编辑

Ice Breaker is comprehensive fullstack app leveraging generative AI and LangChain to find LinkedIn profiles and generate engaging ice breakers. LangChain ReAct agents ensure accurate URL retrieval and JSON cleaning, identifying a summary, facts, topics, and ice breakers. The frontend is built with HTML/CSS, and Flask powers the backend development.

Effortlessly perform sentiment analysis, translation, speech synthesis, summarization, and Q&A tasks with an interactive UI using prompt engineering

Chain of thought adapter for local llms

LLMs are commonly used to rewrite or make stylistic changes to text. The goal is to recover the LLM prompt that was used to transform a given text.