Upload folder using huggingface_hub

.gitattributes

@@ -1,104 +1,2 @@
 # No LFS — all files are under 10MB after compression
-data/clustering/metrics/davies_bouldin_heatmap__BioSimCSE-BioLinkBERT.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__BiomedNLP-BiomedBERT.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__SapBERT-from.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__biobert-large.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__biobert-v1.1.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__bioformer-8L.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__biomed_roberta_base.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__pubmedbert-base.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/davies_bouldin_heatmap__scibert_scivocab_uncased.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__BioSimCSE-BioLinkBERT.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__BiomedNLP-BiomedBERT.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__SapBERT-from.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__biobert-large.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__biobert-v1.1.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__bioformer-8L.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__biomed_roberta_base.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__pubmedbert-base.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/n_clusters_heatmap__scibert_scivocab_uncased.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__BioSimCSE-BioLinkBERT.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__BiomedNLP-BiomedBERT.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__SapBERT-from.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__biobert-large.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__biobert-v1.1.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__bioformer-8L.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__biomed_roberta_base.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__pubmedbert-base.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/metrics/silhouette_heatmap__scibert_scivocab_uncased.png filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
-data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
 data/proteins.json.gz filter=lfs diff=lfs merge=lfs -text

copy_missing_models.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+set -e
+
+SRC="/data/ralmadamonter/llm_project/joint_clustering/join_clustering_grid_second"
+DST="/data/ralmadamonter/llm_dashboard/data/clustering"
+
+for m in allenai__biomed_roberta_base allenai__scibert_scivocab_uncased bioformers__bioformer-8L dmis-lab__biobert-large-cased-v1.1-mnli dmis-lab__biobert-v1.1 microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext; do
+    echo "Copying model=$m ..."
+    cp -r "$SRC/model=$m" "$DST/"
+done
+
+echo "Done. Models in clustering:"
+ls "$DST/"

data/proteins.json.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ca384000c32d8e83bba7b73afb22d3902185d6a90116545bd72a5c6fffdd2d
-size 3667582
+oid sha256:0548623f5c7bf65c60342427c3a9597c8400b54037873d1b10a55a4bfdc9c01c
+size 4701211

upload_to_hf.py

@@ -5,6 +5,6 @@ api.upload_folder(
     folder_path="/data/ralmadamonter/llm_dashboard",
     repo_id="richiam/ProtoPure",
     repo_type="space",
-    ignore_patterns=["*.pyc", "__pycache__", ".git"],
+    ignore_patterns=["*.pyc", "__pycache__", ".git", "data/clustering/"],
 )
 print("Done")