loading
loading
loading
MPT-30B is the latest open-source Large Language Model (LLM) and achieves better performance than GPT-3. In this video, we learn how to use MPT-30B fine-tuned for chat, with LangChain to create an open-source chatbot that can be run on a single GPU. š Notebook: https://github.com/pinecone-io/examples/blob/master/learn/generation/llm-field-guide/mpt/mpt-30b-chatbot.ipynb š² Subscribe for Latest Articles and Videos: https://www.pinecone.io/newsletter-signup/ šš¼ AI Consulting: https://aurelio.ai š¾ Discord: https://discord.gg/c5QtDB9RAP Twitter: https://twitter.com/jamescalam LinkedIn: https://www.linkedin.com/in/jamescalam/ 00:00 MPT-30B Chatbot 00:40 MPT-30B Explained 02:48 Implementing MPT-30B in Python 07:30 Tokenization and Stopping Criteria 09:03 LLM Pipeline in Hugging Face 10:54 Initializing MPT-30B in LangChain 11:25 Building an MPT-30B Chatbot 14:13 Post-Processing Chatbot Responses 17:08 Talking with MPT-30B Chatbot #artificialintelligence #nlp #opensource
The Generative AI and Large Language Models (LLMs) course covers everything you need to know about: - Generative AI - Large Language Models (LLMs) - OpenAI, Cohere, Hugging Face - Managed vs. Open Source - LLM Libraries like LangChain and GPT Index - Long-term memory and retrieval-augmentation And more to come...