HuggingChat

Social Intents brings AI-powered live chat and chatbot automation directly into the collaboration tools your business already uses—Microsoft Teams, Slack, Google Chat, Zoom, and Webex—so your team can engage website visitors without switching platforms. Easily launch advanced ChatGPT, Gemini, and Claude AI chatbots with one click—no coding required. Automate up to 75% of your customer conversations by training your AI assistant on your website content, help docs, and knowledge base. Deliver fast, intelligent answers to common questions and boost your conversion rates with 24/7 automated support. When customers need a human touch, seamlessly escalate chats to your support or sales team inside your existing collaboration environment. Provide real-time live chat, sales assistance, and after-hours customer support—all from tools like Microsoft Teams, Slack, and Google Chat. Whether you're improving customer satisfaction, or capturing more leads, Social Intents can help.

StableVicuna is the first large-scale open source chatbot trained via reinforced learning from human feedback (RHLF). StableVicuna is a further instruction fine tuned and RLHF trained version of Vicuna v0 13b, which is an instruction fine tuned LLaMA 13b model. In order to achieve StableVicuna’s strong performance, we utilize Vicuna as the base model and follow the typical three-stage RLHF pipeline outlined by Steinnon et al. and Ouyang et al. Concretely, we further train the base Vicuna model with supervised finetuning (SFT) using a mixture of three datasets: OpenAssistant Conversations Dataset (OASST1), a human-generated, human-annotated assistant-style conversation corpus comprising 161,443 messages distributed across 66,497 conversation trees, in 35 different languages; GPT4All Prompt Generations, a dataset of 437,605 prompts and responses generated by GPT-3.5 Turbo; And Alpaca, a dataset of 52,000 instructions and demonstrations generated by OpenAI's text-davinci-003.