Update dataset name from htahir1 to zenml namespace in configuration …

…files
zenml-io · Jan 27, 2025 · 86f6276 · 86f6276
1 parent aecfe12
commit 86f6276
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 6 deletions.
diff --git a/llm-finetuning/configs/finetune_aws.yaml b/llm-finetuning/configs/finetune_aws.yaml
@@ -6,7 +6,7 @@ settings:
 model:
   name: "peft-lora-zencoder15B-personal-copilot"
   description: "Fine-tuned `starcoder15B-personal-copilot-A100-40GB-colab` for ZenML pipelines."
-  audience: "Data Scientists / ML Engineers"  
+  audience: "Data Scientists / ML Engineers"
   use_cases: "Code Generation for ZenML MLOps pipelines."
   limitations: "There is no guarantee that this model will work for your use case. Please test it thoroughly before using it in production."
   trade_offs: "This model is optimized for ZenML pipelines. It is not optimized for other libraries."
@@ -23,13 +23,13 @@ steps:
     step_operator: sagemaker-eu
     settings:
       step_operator.sagemaker:
-        estimator_args: 
+        estimator_args:
           instance_type: "ml.p4d.24xlarge"
 
     parameters:
       args:
         model_path: "bigcode/starcoder"
-        dataset_name: "htahir1/zenml-codegen-v1"
+        dataset_name: "zenml/zenml-codegen-v1"
         subset: "data"
         data_column: "content"
         split: "train"

diff --git a/llm-finetuning/configs/finetune_gcp.yaml b/llm-finetuning/configs/finetune_gcp.yaml
@@ -6,7 +6,7 @@ settings:
 model:
   name: "peft-lora-zencoder15B-personal-copilot"
   description: "Fine-tuned `starcoder15B-personal-copilot-A100-40GB-colab` for ZenML pipelines."
-  audience: "Data Scientists / ML Engineers"  
+  audience: "Data Scientists / ML Engineers"
   use_cases: "Code Generation for ZenML MLOps pipelines."
   limitations: "There is no guarantee that this model will work for your use case. Please test it thoroughly before using it in production."
   trade_offs: "This model is optimized for ZenML pipelines. It is not optimized for other libraries."
@@ -29,7 +29,7 @@ steps:
     parameters:
       args:
         model_path: "bigcode/starcoder"
-        dataset_name: "htahir1/zenml-codegen-v1"
+        dataset_name: "zenml/zenml-codegen-v1"
         subset: "data"
         data_column: "content"
         split: "train"

diff --git a/llm-finetuning/configs/generate_code_dataset.yaml b/llm-finetuning/configs/generate_code_dataset.yaml
@@ -10,7 +10,7 @@ settings:
 
 # pipeline configuration
 parameters:
-  dataset_id: htahir1/zenml-codegen-v1
+  dataset_id: zenml/zenml-codegen-v1
 
 steps:
   mirror_repositories: