MAX0MAX
Follow
Lists (2)
Stars
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
🧑🚀 全世界最好的LLM资料总结 | Summary of the world's best LLM resources.
Make websites accessible for AI agents
Task-Aware Agent-driven Prompt Optimization Framework
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Official inference library for Mistral models
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Stable Diffusion web UI
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
Doing simple retrieval from LLM models at various context lengths to measure accuracy
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
Survey of Small Language Models from Penn State, ...
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
[ICLR 2024] SWE-bench: Can Language Models Resolve Real-world Github Issues?
A unified evaluation framework for large language models
Machine Learning Journal for Intermediate to Advanced Topics.
Let your Claude able to think
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
DSPy: The framework for programming—not prompting—language models
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
Generative Agents: Interactive Simulacra of Human Behavior
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…