fix: Use Alphabet 10k sample dataset.

GoogleCloudPlatform · May 23, 2024 · d271b5d · d271b5d
1 parent a0427e5
commit d271b5d
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/ai-platform/snippets/embedding-model-tuning.js b/ai-platform/snippets/embedding-model-tuning.js
@@ -24,10 +24,10 @@ async function main(
   pipelineJobDisplayName = 'embedding-customization-pipeline-sample',
   baseModelVersionId = 'text-embedding-004',
   taskType = 'DEFAULT',
-  queriesPath = 'gs://embedding-customization-pipeline/dataset/queries.jsonl',
-  corpusPath = 'gs://embedding-customization-pipeline/dataset/corpus.jsonl',
-  trainLabelPath = 'gs://embedding-customization-pipeline/dataset/train.tsv',
-  testLabelPath = 'gs://embedding-customization-pipeline/dataset/test.tsv',
+  corpusPath = 'gs://cloud-samples-data/ai-platform/embedding/goog-10k-2024/r11/corpus.jsonl',
+  queriesPath = 'gs://cloud-samples-data/ai-platform/embedding/goog-10k-2024/r11/queries.jsonl',
+  trainLabelPath = 'gs://cloud-samples-data/ai-platform/embedding/goog-10k-2024/r11/train.tsv',
+  testLabelPath = 'gs://cloud-samples-data/ai-platform/embedding/goog-10k-2024/r11/test.tsv',
   outputDimensionality = 768,
   learningRateMultiplier = 1.0,
   batchSize = 128,