OpenChatKit

OpenChatKit is an open-source project that provides a powerful base to create both specialized and general-purpose chatbots for various applications.

To use OpenChatKit, you can visit the OpenChatKit website and try out the demo. You can also access the source code, model weights, and training datasets on GitHub. For more information on how to use OpenChatKit and give feedback, you can join the OpenChatKit community on GitHub, Discord, Twitter, and Medium.

OpenChatKit is an open-source project that provides a powerful base to create both specialized and general purpose chatbots for various applications. It consists of four key components: an instruction-tuned large language model, customization recipes to fine-tune the model, an extensible retrieval system to augment the model with live-updating information, and a moderation model to filter inappropriate or out-of-domain questions.

OpenChatKit is a collaboration between Together, LAION, and Ontocord. They created the OIG-43M dataset, a collection of 43 million high-quality instructions for conversational interactions, and the moderation dataset, a collection of inappropriate questions for chatbots.

You can try out OpenChatKit on the OpenChatKit website and give feedback through the OpenChatKit feedback app. You can also join the OpenChatKit community on GitHub, Discord, Twitter, and Medium to share your ideas, suggestions, and questions.

The base model of OpenChatKit is GPT-NeoXT-Chat-Base-20B, a 20 billion parameter large language model based on EleutherAI’s GPT-NeoX model. It is fine-tuned with the OIG-43M dataset, focusing on several tasks such as multi-turn dialogue, question answering, classification, extraction, and summarization.

OpenChatKit performs well on a broad set of natural language tasks, especially those involving question and answering, extraction, and classification. However, there are also areas where OpenChatKit needs improvement, such as knowledge-based closed question and answering, coding tasks, repetition, context switching, and creative writing and longer answers.

You can cite or reference OpenChatKit or the training datasets in your work by using the provided BibTeX entries in the GitHub repository.

OpenChatKit compares favorably with other large language models or chatbots in terms of its versatility, customizability, and extensibility. It can handle a wide range of natural language tasks with high performance, and it can be fine-tuned and adapted for specific applications or domains with the provided tools and recipes.

OpenChatKit is licensed under the Apache License 2.0, which allows you to freely use, modify, and distribute the software. You can also inspect the weights of the model using the Hugging Face Transformers library or the Jupyter notebooks provided in the GitHub repository.

You can access the source code, model weights, and training datasets of OpenChatKit on GitHub. The model weights and datasets can also be downloaded from Hugging Face.