Papers
arxiv:2305.14233

Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Published on May 23, 2023
Β· Featured in Daily Papers on May 24, 2023
Authors:
,
,
,
,
,
,

Abstract

Fine-tuning on instruction data has been widely validated as an effective practice for implementing chat language models like ChatGPT. Scaling the diversity and quality of such data, although straightforward, stands a great chance of leading to improved performance. This paper aims to improve the upper bound of open-source models further. We first provide a systematically designed, diverse, informative, large-scale dataset of instructional conversations, UltraChat, which does not involve human queries. Our objective is to capture the breadth of interactions that a human might have with an AI assistant and employs a comprehensive framework to generate multi-turn conversation iteratively. UltraChat contains 1.5 million high-quality multi-turn dialogues and covers a wide range of topics and instructions. Our statistical analysis of UltraChat reveals its superiority in various key metrics, including scale, average length, diversity, coherence, etc., solidifying its position as a leading open-source dataset. Building upon UltraChat, we fine-tune a LLaMA model to create a powerful conversational model, UltraLLaMA. Our evaluations indicate that UltraLLaMA consistently outperforms other open-source models, including Vicuna, the previously recognized state-of-the-art open-source model. The dataset and the model will be publicly released\url{https://github.com/thunlp/UltraChat}.

Community

will we be able to make a quantized version for cpu's? and what are the stats on RAM usage and such?

θ‘Œη™Ύι‡Œθ€…εŠδΉεοΌŒε“ˆε“ˆε“ˆ
image.png

This comment has been hidden
This comment has been hidden

Sign up or log in to comment

Models citing this paper 6

Browse 6 models citing this paper

Datasets citing this paper 9

Browse 9 datasets citing this paper

Spaces citing this paper 18

Collections including this paper 2