Transforming a generalist Large Language Model into a specialized financial expert using just a CPU! In this video, we walk you through the fine-tuning process with a hands-on example in financial sentiment analysis. Learn how to harness the power of fine-tuning to analyze financial tweets and make informed investment decisions. Follow the link for the full code and a step-by-step guide! 💼📈🚀
► Jump on our free LLM course from the Gen AI 360 Foundational Model Certification (Built in collaboration with Activeloop, Towards AI, and the Intel Disruptor Initiative): learn.activeloop.ai/courses/l...
► Google Colab Notebook: colab.research.google.com/dri...
With the great support of Cohere & Lambda.
► Course Official Discord: / discord
► Activeloop Slack: slack.activeloop.ai/
► Activeloop KZitem: / @activeloop
►Follow me on Twitter: / whats_ai
►My Newsletter (A new AI application explained weekly to your emails!): www.louisbouchard.ai/newsletter/
►Support me on Patreon: / whatsai
How to start in AI/ML - A Complete Guide:
►www.louisbouchard.ai/learnai/
Become a member of the KZitem community, support my work and get a cool Discord role :
/ @whatsai
Chapters:
0:00 Give a thumbs-up to the video and subscribe for more! If you read this, I wish you a fantastic day!
0:36 What is fine-tuning?
1:46 Loading the dataset using DeepLake.
3:13 Structure the training prompt.
3:28 Load tokenizer and create dataset object.
4:27 Initialize the Lora config and training hyperparameters.
6:02 Download and load the model into memory.
6:42 Casting specific layers within the network to complete 32-bit precision.
7:00 Creating the trainer and launching the training process.
7:22 Merging the trained LoRA adapters to the base model.
7:47 Inference time!
8:22 Conclusion.
#ai #languagemodels #llm
Негізгі бет Ғылым және технология How to Fine-Tune your LLM on Tweets! (large language models for investing)
Пікірлер: 2