What does the term "distillation" refer to in the context of large language models (LLMs)?
이 연습은 강의의 일부입니다
이론을 실습으로 바꾸는 인터랙티브 연습 중 하나를 만나보세요
Get introduced to the core generative AI concepts and the Snowflake capabilities that bring them to life. You'll set up your Snowflake environment, work in Snowflake Notebooks, and build a simple AI app that loads unstructured call-transcript data from an S3 bucket, prompts a foundation model to summarize it as JSON, and surfaces the results in a Streamlit UI.
Dive into Snowflake Cortex's LLM-based functions to accomplish a wide range of AI tasks. You'll implement common use cases like summarization, translation, sentiment analysis, and text classification with task-specific functions, run open-ended prompts through the Cortex COMPLETE function with Llama, Mistral, and Anthropic models, choose the right LLM for the job, and use helper functions to estimate token count and cost before you spend it.
Customize LLM responses for your use case with Cortex Fine-Tuning. You'll learn how Parameter Efficient Fine-Tuning lowers data requirements and cost, generate and split training data, fine-tune Mistral-7b to respond in a specific style using the Cortex FINETUNE function and the no-code AI/ML Studio, test your fine-tuned model with COMPLETE, and build a Streamlit app that auto-generates custom emails and text messages.
현재 연습
