Are LLMs really ready for production deployment?
I think that all the examples seen during the sessions are LLMs already in production, so I guess yes.
Tensorboard is a way to help see stats and debug.Is there an equivalent way where we can see network traffic from downloading LLM to submitting any data as we train our models? Besides engaging our network security team, is there such a tool that we...
I am working on generative AI. Does Databricks offer databases for storing vector embeddings, if yes, how efficient are they.
The summit is fabulous !
How do we migrate and host an existing Python model onto Databricks?
Use MLflow features like tracking and embed mlflow wrapper into your existing python script to log and register in the Databricks model registry.There are handful Mlflow Api available in the documentation.
extremely subjective (human responses on likert scale don't suffice and hard to quantify with one metric on accuracy). curious how others have approached this
There aren't exact metrics to evaluate how LLM is accurate right now. Just make test questions have a large coverage could be a tip. I expect many people will work on it!
Love how easy it is to create a search retrieval product with databricks.
Where Data Scientists goes to camp? to a Random Forest.
#Summit23Hippy to know about it
As Databricks starts with their ML engines on their marketplace, anyone know or have financial industry models? Would this solution be better than building our own?
Super excited about the recent acquisition of MosiacML. Can't wait to learn and demo the new features.
How is the new feature sharing capabilities help us to share our model features with our kubernetes models
Hi All,I am unable to execute "Classroom-Setup-02.2" setup in Data Engineering Course. There is the following error: FileNotFoundError: [errno 2] no such file or directory: '/dbfs/mnt/dbacademy-datasets/data-engineer-learning-path/v01/ecommerce/raw/u...
I had the same problem. There is another post with the same issue. And I got answer there. See below.Problems with pandas.read_parquet() and path - Databricks - 19655
Collaborate with prospects. LLMs and vector store
Are you using the vector db or libraries for your project?
