본문 바로가기

분류 전체보기245

ChatGPT학습방법 system 역할에서 다음과 같은 지시를 할 수 있습니다: Domain Expertise: "You are an assistant trained in the information, products, and services offered by Exbody"라고 지시할 수 있습니다. 이렇게 하면 assistant는 Exbody 회사와 그 제품 및 서비스에 대한 전문 지식을 가진 것으로 가정하고 응답을 생성할 것입니다. Behavioral Context: "Your primary role is to answer questions related to Exbody's products, services, and general information"라고 추가 지시할 수 있습니다. 이로써 assistant는 Exbod.. 2023. 9. 18.
wuerstchen https://huggingface.co/blog/wuerstchen Introducing Würstchen: Fast Diffusion for Image Generation Introducing Würstchen: Fast Diffusion for Image Generation What is Würstchen? Würstchen is a diffusion model, whose text-conditional component works in a highly compressed latent space of images. Why is this important? Compressing data can reduce comput huggingface.co https://huggingface.co/docs/dif.. 2023. 9. 17.
Stable Audio https://stability.ai/research/stable-audio-efficient-timing-latent-diffusion Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion — Stability AI Stable Audio represents the cutting-edge audio generation research by Stability AI’s generative audio research lab, Harmonai. We continue to improve our model architectures, datasets, and training procedures to improve output quality, controllab.. 2023. 9. 17.
ChatGPT dataset https://github.com/voidful/awesome-chatgpt-dataset GitHub - voidful/awesome-chatgpt-dataset: Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT! Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT! - GitHub - voidful/awesome-chatgpt-dataset: Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT! github.com https://huggingface.co/da.. 2023. 9. 14.