Hi Everyone, I work at Together. Today we released OpenChatKit: an open-source base to create chatbots for various applications. More than a model release, this is the beginning of an open source project. We are releasing a set of tools and processes for ongoing improvement with community contributions.<p>You can try it now on Hugging Face!
<a href="https://huggingface.co/spaces/togethercomputer/OpenChatKit" rel="nofollow">https://huggingface.co/spaces/togethercomputer/OpenChatKit</a><p>OpenChatKit includes 4 key components:<p>1. An instruction-tuned large language model, fine-tuned for chat from EleutherAI’s GPT-NeoX-20B with over 43 million instructions on 100% carbon negative compute available under Apache-2.0 license on Hugging Face.<p>2. A set of customization recipes to fine-tune the model to achieve high accuracy on your tasks documented and available as open-source under the Apache-2.0 license on Github, along with code to recreate our model results.<p>3. An extensible retrieval system enabling you to augment bot responses with information from a document repository, API, or other live-updating information source at inference time, with open-source examples for using Wikipedia or a web search API.<p>4. A moderation model, fine-tuned from GPT-JT-6B, designed to filter which questions the bot responds to, also available under the Apache-2.0 license on Hugging Face.<p>We collaborated with the tremendous communities at @laion_ai and Ontocord to create the training dataset used for these models, also released as open-source. Read the full details on LAION's blog post!<p>Can't wait to hear your feedback!<p>Thanks,
-Together