cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 
Help
Machine Learning
Dive into the world of machine learning on the Databricks platform. Explore discussions on algorithms, model training, deployment, and more. Connect with ML enthusiasts and experts.
cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Start a conversation
Sujitha
by • Databricks Employee
  • 4033 Views
  • 3 replies
  • 2 kudos

Resolved! Hello Community Users,  We recently announced a new Large Language Models (LLM) program, the first of its kind on edX! Learn how to develop production...

Hello Community Users, We recently announced a new Large Language Models (LLM) program, the first of its kind on edX! Learn how to develop production-ready LLM applications and dive into the theory behind foundation models. Taught by industry experts...

Machine Learning
Reply
  • 4033 Views
  • 3 replies
  • 2 kudos
View Replies
Latest Reply
APadmanabhan
Databricks Employee
  • 2 kudos

Hi @163050 You could download the Dbc file from the course, we already have the LLM course in the Customer Academy.

  • 2 kudos
2 More Replies
HT
by • New Contributor II
  • 10526 Views
  • 5 replies
  • 2 kudos

Trying out Dolly - how to load pytorch_model.bin so it's not downloading it every time the cluster is restarted

Hi, I am new to LLM and am curious to try it out. I did the following code to test from the databricks website:import torch from transformers import pipeline instruct_pipeline = pipeline(model="databricks/dolly-v2-12b", torch_dtype=torch.bfloat16, tr...

Machine Learning
Reply
  • 10526 Views
  • 5 replies
  • 2 kudos
View Replies
Latest Reply
sean_owen
Databricks Employee
  • 2 kudos

Just set the HF cache dir to a persistent path on /dbfs:import os os.environ['TRANSFORMERS_CACHE'] = "/dbfs/..."

  • 2 kudos
4 More Replies
JAHNAVI
by • Databricks Employee
  • 7028 Views
  • 1 replies
  • 2 kudos

Resolved! error in running a LLM model in pyfunc.spark_udf

error in running a LLM model in pyfunc.spark_udf

Machine Learning
Reply
  • 7028 Views
  • 1 replies
  • 2 kudos
View Replies
Latest Reply
JAHNAVI
Databricks Employee
  • 2 kudos

Solution:   Please find below the example. Creating a secret and scope is a one time activity once we create a scope and secret we can access the token using any notebook or cluster in the workspace as shown below. After creating a secret if we want ...

  • 2 kudos
Labels