diff --git a/tutorials/pretraining-data-curation/red-pajama-v2-curation-tutorial.ipynb b/tutorials/pretraining-data-curation/red-pajama-v2-curation-tutorial.ipynb index 42c92bfab..0d1e23a85 100644 --- a/tutorials/pretraining-data-curation/red-pajama-v2-curation-tutorial.ipynb +++ b/tutorials/pretraining-data-curation/red-pajama-v2-curation-tutorial.ipynb @@ -2692,7 +2692,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "id": "6bee85f3-5477-4b9c-b606-7bbbefbe6cfc", "metadata": { "tags": [] @@ -2749,7 +2749,6 @@ " cache_dir=cache_dir,\n", " jaccard_pairs_path=jaccard_pairs_path,\n", " id_column=id_field,\n", - " convert_str_ids=True,\n", " jaccard_threshold=jaccard_threshold,\n", ")\n", "components_stage.cc_workflow(output_path=output_path)\n", @@ -4416,7 +4415,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "id": "89398db9-d4e6-48ec-bad8-1d5ac553cadd", "metadata": { "tags": [] @@ -4454,7 +4453,6 @@ " cache_dir=cache_dir,\n", " jaccard_pairs_path=jaccard_pairs_path,\n", " id_column=id_field,\n", - " convert_str_ids=True,\n", " jaccard_threshold=jaccard_threshold,\n", ")\n", "components_stage.cc_workflow(output_path=output_path)\n", diff --git a/tutorials/single_node_tutorial/single_gpu_tutorial.ipynb b/tutorials/single_node_tutorial/single_gpu_tutorial.ipynb index de585e08d..3170b3502 100644 --- a/tutorials/single_node_tutorial/single_gpu_tutorial.ipynb +++ b/tutorials/single_node_tutorial/single_gpu_tutorial.ipynb @@ -1749,7 +1749,6 @@ " cache_dir=connected_component_cache_dir,\n", " jaccard_pairs_path=jaccard_pairs_path,\n", " id_column=input_id_field,\n", - " convert_str_ids=True,\n", " jaccard_threshold=jaccard_threshold,\n", ")\n", "\n", diff --git a/tutorials/zyda2-tutorial/1_fuzzy_dedup/3_connected_components.py b/tutorials/zyda2-tutorial/1_fuzzy_dedup/3_connected_components.py index 67796ec45..467e3c4e2 100644 --- a/tutorials/zyda2-tutorial/1_fuzzy_dedup/3_connected_components.py +++ b/tutorials/zyda2-tutorial/1_fuzzy_dedup/3_connected_components.py @@ -41,7 +41,6 @@ cache_dir=connected_component_cache_dir, jaccard_pairs_path=buckets_to_edges_out, id_column=input_id_field, - convert_str_ids=True, ) # Load and run connected components