![]() ![]() ![]() Task Planning: Using ChatGPT to analyze the requests of users to understand their intention, and disassemble them into possible solvable tasks.The workflow of our system consists of four stages: We introduce a collaborative system that consists of an LLM as the controller and numerous expert models as collaborative executors (from HuggingFace Hub). See our paper: HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace, Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu and Yueting Zhuang (the first two authors contribute equally) Language serves as an interface for LLMs to connect numerous AI models for solving complicated AI tasks! We updated a version of code for building.Just run python awesome_chat.py -config configs/ to experience it.You can enjoy a lightweight experience with Jarvis without deploying the models locally.We added the CLI mode and provided parameters for configuring the scale of local endpoints.The Web API /tasks and /results access intermediate results for Stage #1: task planning and Stage #1-3: model selection with execution results.(Build with inference_mode=hybrid and local_deployment=standard) The Gradio demo is now hosted on Hugging Face Space. ![]() ![]() We added the Gradio demo and built the web API for /tasks and /results in server mode.Jarvis now supports the OpenAI service on the Azure platform and the GPT-4 model.This project is under construction and we will have all the code ready soon. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |