accelerated-data-science
accelerated-data-science copied to clipboard
oracle
ADS is the Oracle Data Science Cloud Service's python SDK supporting, model ops (train/eval/deploy), along with running workloads on Jobs and Pipeline resources.
When deleting a job, there is an option to `force_delete` all job runs. However, job run can only be cancelled if it is "in progress", "accepted" or "need attention". Otherwise...
## Description This work in progress PR introduces refactored code for LangChain integration. The core concept behind the new version is the introduction of a base class, `OCIModelDeployment`, within the...
### Oracle-ads version used - [X] I have checked that this issue has not already been reported. - [X] I have confirmed this bug exists on the [latest version](https://https://github.com/oracle/accelerated-data-science/releases/) of...
### Oracle-ads version used - [X] I have checked that this issue has not already been reported. - [X] I have confirmed this bug exists on the [latest version](https://https://github.com/oracle/accelerated-data-science/releases/) of...
## Description This PR is to show the all the changes that will be included into the AQUA V1.0.4 release.
### Fix validation for model containing both formats. - Currently the logic to validate model only takes care of either `SAFETENSORS` or `GGUF` format and misses the case when both...
## Summary This PR implements support for two new Gen AI metrics - Perpelexity & Text Readability. *** ## Changes 1. In ads/aqua/evaluation/evaluation.py - Add two new metrics `perplexity_score` &...
