by
hawa
• New Contributor II
- 1087 Views
- 2 replies
- 2 kudos
Hi, I've encountered a problem of serving a langchain model I just created successfully on Databricks.I was using the following code to set up a model in unity catalog:from mlflow.models import infer_signatureimport mlflowimport langchainmlflow.set_r...
- 1087 Views
- 2 replies
- 2 kudos
Latest Reply
I suspected the issue is coming from this small error I got: Got error: Must specify a chain Type in config. I used the chain_type="stuff" when building the langchain but I'm not sure how to fix it.
1 More Replies
- 294 Views
- 2 replies
- 1 kudos
Hi Team, I have my databricks environment where I want to deploy, train and monitor ML model in automated way(github action). How I can do that?
- 294 Views
- 2 replies
- 1 kudos
Latest Reply
Hi there @ncparab13,- https://docs.databricks.com/aws/en/dev-tools/bundles/mlops-stacks ,- https://docs.databricks.com/aws/en/machine-learning/mlops/ci-cd-for-ml , - https://docs.databricks.com/aws/en/repos/ci-cd-techniques-with-reposHere are some li...
1 More Replies
by
Leo69
• New Contributor II
- 1691 Views
- 1 replies
- 1 kudos
Hello everyone,I have an Azure Databricks subscription with my company, and I want to use external LLMs in databricks, like claude-3 or gemini. I managed to create a serving endpoint for Anthropic and I am able to use claude 3.But I want to use a Gem...
- 1691 Views
- 1 replies
- 1 kudos
Latest Reply
With support from a helpful Databricks employee, we found out that the problem was that the `private_key` / `private_key_plaintext` field needs to be the entire JSON object that GCP creates for the service account not just the private key string from...
by
yhyhy3
• New Contributor III
- 1416 Views
- 2 replies
- 0 kudos
I saw that Foundation Model API is not HIPAA compliant. Is there a timeline in which we could expect it to be HIPAA compliant? I work for a healthcare company with a BAA with Databricks.
- 1416 Views
- 2 replies
- 0 kudos
Latest Reply
It is now HIPAA compliant: Provisioned throughput endpoints are available with compliance certifications like HIPAA, Model Serving is HIPAA compliant in all regions
1 More Replies
- 17719 Views
- 3 replies
- 0 kudos
I want learn about Machine Learning operations but I can't access this page.https://www.databricks.com/training/catalog/advanced-machine-learning-operations-3508 Access deniedYou do not have permission to access this page, please contact your admini...
- 17719 Views
- 3 replies
- 0 kudos
Latest Reply
Hello, @ash1127!Please file a ticket with the Databricks support team to get assistance with this issue.Thank you.
2 More Replies
- 556 Views
- 0 replies
- 0 kudos
When it comes to machine learning, the platform plays a pivotal role in successful implementation. Databricks offers a best-in-class machine learning platform with cutting-edge features such as MLflow, Model Registry, Feature Store, and MLOps, which ...
- 556 Views
- 0 replies
- 0 kudos
- 1144 Views
- 2 replies
- 2 kudos
We are trying to train a predictive ML model using the XGBoost Classifier. Part of the requirements we have gotten from our business team is to implement feature weighting as they have defined certain features mattering more than others. We have 69 f...
- 1144 Views
- 2 replies
- 2 kudos
Latest Reply
Hello @sjohnston2 here is some information i found internally:
Possible Causes
Memory Access Issue: The segmentation fault suggests that the program is trying to access memory that it's not allowed to, which could be caused by an internal bug in XGBo...
1 More Replies
- 649 Views
- 2 replies
- 1 kudos
Hi, I've got a question about deploying an endpoint for Llama 3.1 8b. The following code should create the endpoint without scale-to-zero. The endpoint is being created, but with scale-to-zero, although scale_to_zero_enabled is set to False. Instead ...
- 649 Views
- 2 replies
- 1 kudos
Latest Reply
Thanks for the reply @Walter_C. This didn't quite work, since it used a CPU and didn't consider the max_provisioned_throughput, but I finally got it to work like this: from mlflow.deployments import get_deploy_client
client = get_deploy_client("data...
1 More Replies
- 2839 Views
- 1 replies
- 0 kudos
I'm using a Single Node machine with g5-2x-large to fine tune a LLaMa-2 model. My Come Notebook runs very smoothly on Google Col but when I try to run it on `Databricks`, it throws me the exact error given below:RuntimeError: Expected to mark a varia...
- 2839 Views
- 1 replies
- 0 kudos
Latest Reply
Hello @saleem_shady!
Have you tried including the parameter ddp_find_unused_parameters=False in your TrainingArguments? Here's an example of how to include it: https://github.com/databricks/databricks-ml-examples/blob/master/llm-models/llamav2/llamav...
by
amal15
• New Contributor II
- 1604 Views
- 1 replies
- 0 kudos
error: not found: type XGBoostEstimator Spark & Scala
- 1604 Views
- 1 replies
- 0 kudos
Latest Reply
@amal15 - can you please include the below to the import statement and see if it works.
ml.dmlc.xgboost4j.scala.spark.XGBoostEstimator
- 1876 Views
- 0 replies
- 0 kudos
I am looking for the more detailed resources comparing RAG to fine-tuning methods in AI models to processing text data with LLM in laymen notes. I have found one resource but looking for the more detailed view https://www.softwebsolutions.com/resour...
- 1876 Views
- 0 replies
- 0 kudos
by
Sam
• New Contributor III
- 2836 Views
- 0 replies
- 0 kudos
Hi,I have a transformer model from Hugging Face I have logged to MLFlow.When I load in using mlflow.transformers.load_model I receive a bunch of warnings: WARNING:urllib3.connectionpool:Connection pool is full, discarding connection: xxxx. Connection...
- 2836 Views
- 0 replies
- 0 kudos
by
GKH
• New Contributor II
- 2664 Views
- 1 replies
- 1 kudos
We have deployed Dolly (https://huggingface.co/databricks/dolly-v2-3b) as a REST API endpoint on our infrastructure. The notebook we used to do this is included in the text below my question.The Databricks infra used had the following config - (13.2...
- 2664 Views
- 1 replies
- 1 kudos
Latest Reply
I had a similar problem when I used HuggingFacePipeline(pipeline=generate_text) with langchain. It worked to me when I tried to use HuggingFaceHub instead. I used the same dolly-3b model.
- 1714 Views
- 0 replies
- 0 kudos
I upgraded Tensorflow on Databricks notebook using %pip command. Now when running the training job, I get this error: "DNN library initialization failed."
- 1714 Views
- 0 replies
- 0 kudos
- 2251 Views
- 1 replies
- 0 kudos
Hi,I'm trying to enable inference table for my llama_2_7b_hf serving endpoint, however I'm getting the following error:"Inference tables are currently not available with accelerated inference." Anyone one have an idea on how to overcome this issue? C...
- 2251 Views
- 1 replies
- 0 kudos
Latest Reply
From the information you provided, it seems like you are trying to enable inference tables for an existing endpoint. However, the error message suggests that this feature may not be supported with accelerated inference.If you have previously disabled...