- 2299 Views
- 2 replies
- 0 kudos
Model Serving Latency Chart
Hi, For the model serving latency graph what is p50 and p99? I only have one model i am serving on this endpoing so im surprised to see two models being tracked
- 2299 Views
- 2 replies
- 0 kudos
- 0 kudos
If im not mistaken this refers to 50% of responses and 99% responses and averages accordingly for the metrics? @s_park @Sujitha @Debayan
- 0 kudos
- 2344 Views
- 3 replies
- 0 kudos
Unable to create serving endpoint for the huggingface model phi-3-mini-128k-instruct
#20 69.92 ERROR: Could not find a version that satisfies the requirement transformers==4.41.0.dev0 (from versions: 0.1, 2.0.0, 2.1.0, 2.1.1, 2.2.0, 2.2.1, 2.2.2, 2.3.0, 2.4.0, 2.4.1, 2.5.0, 2.5.1, 2.6.0, 2.7.0, 2.8.0, 2.9.0, 2.9.1, 2.10.0, 2.11.0, 3....
- 2344 Views
- 3 replies
- 0 kudos
- 814 Views
- 0 replies
- 0 kudos
Model Serving - Shadow Deployment - Azure
Hey,I'm composing an architecture within the usage of Model Serving Endpoints and one of the needs that we're aiming to resolve is Shadow Deployment.Currently, it seems that the traffic configurations available in model serving do not allow this type...
- 814 Views
- 0 replies
- 0 kudos
- 1407 Views
- 0 replies
- 0 kudos
"error_code":"INVALID_PARAMETER_VALUE","message":"INVALID_PARAMETER_VALUE: Failed to generate access
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...
- 1407 Views
- 0 replies
- 0 kudos
- 1743 Views
- 0 replies
- 0 kudos
How to fine-tune OpenAI’s large language models (LLMs)
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...
- 1743 Views
- 0 replies
- 0 kudos
- 1022 Views
- 1 replies
- 0 kudos
Spacy Retraining failure
Hello, I'm having problems trying to run my retraining notebook for a spacy model. The notebook creates a shell file with the following lines of code: cmd = f''' awk '{{sub("source = ","source = /dbfs/FileStore/{dbfs_folder}/textcat/categories...
- 1022 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @AndersenHuang, Thank you for contacting Databricks community support. The error message you're encountering suggests that there's a permission issue when trying to copy the files. It's possible that the permissions for the directory /dbfs/FileSto...
- 0 kudos
- 1814 Views
- 3 replies
- 0 kudos
Import mlflow Error
Hello, I am trying to replicate this motebook in my environment: mlflow-end-to-end-example - Databricks However, I am getting the following error when I run "import mlflow": "TypeError: bases must be types"How can I solve this issue? Thank you, Tanji...
- 1814 Views
- 3 replies
- 0 kudos
- 0 kudos
Hello @tanjil Thank you for contacting databricks community support. Could you check what version of protobuf you have? If you are using 10.4 ML cluster, the MLflow 1.x is not compatible with protobuf 4.x. The default version of protobuf in MLR 10...
- 0 kudos
- 858 Views
- 1 replies
- 0 kudos
while registering model I am getting error: AssertionError:
while registering model I am getting error: AssertionError:I am getting error while running the code with workflow if I running code individually with notebook then its running fine. below is the code : fe = FeatureEngineeringClient() ...
- 858 Views
- 1 replies
- 0 kudos
- 0 kudos
Hi @ml-engineer Thank you for contacting Databricks community support. I think you are installing tensorflow version 2.14, could you update to 2.16 using the pip install --upgrade tensorflow and see how it works?
- 0 kudos
- 845 Views
- 1 replies
- 0 kudos
GenAI democratizes AI field
Interesting to hear the latest tech trend at Data +AI summit.
- 845 Views
- 1 replies
- 0 kudos
- 0 kudos
you can find the synthesis on a DAIS 2023 announcements here : https://medium.com/@youssefmrini/data-and-ai-summit-2023-announcements-6a4aade1d54c
- 0 kudos
- 3229 Views
- 3 replies
- 0 kudos
Resolved! Problems with xgboost.spark model loading from MLflow.
When loading an xgboost model from mlflow following the provided instructions in Databricks hosted MLflow the input sizes I am showing on the job are over 1 TB. Is anyone else using an xgboost.spark model and noticing the same behavior? Below are som...
- 3229 Views
- 3 replies
- 0 kudos
- 0 kudos
Thank you very much @Data_Cowboy !!! I had the same issue. I even had 14 TiB Databricks should really fix this
- 0 kudos
- 1011 Views
- 1 replies
- 0 kudos
Use OF API from package enerbitdso 0.1.8 PYPI
Hello! I have code to use an API supplied in the energitdso package (This is the repository https://pypi.org/project/enerbitdso/). I changed the code adapting it to AZURE DATABRICKS in python, but although there is a connection with the API, it does ...
- 1011 Views
- 1 replies
- 0 kudos
- 0 kudos
The owner of the package updated it to use the time out as a parameter of up to 20 seconds and updated a dependent package in DataBricks, with the above the problem was solved
- 0 kudos
- 1952 Views
- 1 replies
- 0 kudos
RBAC and VectorSearch
When implementing the managed VectorSearch, what is the preferred way to implement row based access control? I see that you can use the filter API during a query, so simple filters using a certain column may work, but what if all the security informa...
- 1952 Views
- 1 replies
- 0 kudos
- 0 kudos
Thanks AI for summarizing my question. However, you did not actually answer it.
- 0 kudos
- 1284 Views
- 0 replies
- 0 kudos
Optimal Cluster Configuration for Training on Billion-Row Datasets
Hello Databricks Community,I am currently facing a challenge in configuring a cluster for training machine learning models on a dataset consisting of approximately a billion rows and 40 features. Given the volume of data, I want to ensure that the cl...
- 1284 Views
- 0 replies
- 0 kudos
- 2473 Views
- 0 replies
- 0 kudos
Help - org.apache.spark.SparkException: Job aborted due to stage failure: Task 47 in stage 2842.0
Hello, I am training a SparkXGBRegressor model. It runs without errors if the complexity is low, however when I increase the max_depth and/or num_parallel_tree parameters, I get an error. I checked the cluster metrics during training and it doesn't l...
- 2473 Views
- 0 replies
- 0 kudos
- 3913 Views
- 2 replies
- 1 kudos
How to fix this runtime error in this Databricks distributed training tutorial workbook
I am following along with this notebook found from this article. I am attempting to fine tune the model with a single node and multiple GPUs, so I run everything up to the "Run Local Training" section, but from there I skip to "Run distributed traini...
- 3913 Views
- 2 replies
- 1 kudos
- 1 kudos
Hi AChang, have you eventually resolved the error? I've also having the same error.
- 1 kudos
