Yin Song

Hi @vdantu Thx for your reply! When deployed an multi-model-server, I could invoke different model for inference by set the **TargetModel** parameter in InvokeEndpoint (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_runtime_InvokeEndpoint.html). It is not clear to...

Pls see the example code at https://github.com/aws-samples/amazon-sagemaker-predict-electricity-demand-with-custom-gluonts-container/blob/main/02_deploy_gluonts_forecast_models_as_multi_model_endpoints.ipynb

The MMS does not seem to support batch transform directly, to perform batch tranform. We need to create models seperately in Sagemaker, and do the batch transform for each model...

`git checkout tags/v0.4.1` using v0.4.1 might fix the issue.

This is because - https://github.com/EleutherAI/lm-evaluation-harness/blob/v0.4.2/lm_eval/filters/extraction.py#L34 could match empty patterns, like [('', '', '', '', '')] - https://github.com/EleutherAI/lm-evaluation-harness/blob/v0.4.2/lm_eval/filters/extraction.py#L36 could match empty patterns, like ('', '', '', '', ''). It would cause...

Have u run scripts/set_up_sagemaker.sh?

I suspect haven't properly cloned the submodules `git clone --recurse-submodules https://github.com/aws-samples/amazon-sagemaker-tsp-deep-rl.git`. Then the files in `learning-tsp` folder are missing. If you wanted to manually copy the required files, you need...

> I find that the error appears when the obj_episode_id is 11 in any scripts that define obj-variation-mode as the episode. I had similar issue, but when I `sudo apt-get...