Updated model with better training and evaluation. Test and val data included as pickle files. Older Legacy files were removed to avoid confusion.

.gitattributes

@@ -1,42 +1,5 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
-.git/lfs/objects/3e/02/3e02186ca2008bfd4ebb104de46ce9beba276ae45c453fedfaeda087cc99f02e filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/3e/6b/3e6bdbead621753c09514da26bdf850f9758533dfd9d599e6ee947c8daea59e4 filter=lfs diff=lfs merge=lfs -text
 .git/lfs/objects/21/3e/213e31b950d84bee8f77e75c3cd557932d9bc7dc76dcd03aba223c2e4f841a0f filter=lfs diff=lfs merge=lfs -text
-.git/lfs/objects/3f/07/3f07f428adbf03a3e7902665664f5dd6f342a6b6c7a2a47a7026772c48cb0e73 filter=lfs diff=lfs merge=lfs -text
-.git/lfs/objects/3d/42/3d42ebe4f358451d3fde5790fe6516dcd94dc0e5c0159c25ebfe679e11eab41d filter=lfs diff=lfs merge=lfs -text
-.git/lfs/objects/82/e8/82e8a4b706199c597b03c69c5184163d6bded50042bbb9e85f3928b2f5be3818 filter=lfs diff=lfs merge=lfs -text
+test_data.pickle filter=lfs diff=lfs merge=lfs -text
+val_data.pickle filter=lfs diff=lfs merge=lfs -text

Information-Retrieval_evaluation_eval_results.csv

@@ -0,0 +1,6 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100
+0,0,0.7225806451612903,0.8580645161290322,0.9096774193548387,0.9419354838709677,0.7225806451612903,0.7161290322580646,0.2860215053763441,0.8516129032258064,0.18193548387096772,0.9032258064516129,0.09419354838709676,0.9354838709677419,0.7968433179723501,0.8271966295960388,0.7941603020635278
+0,0,0.40836012861736337,0.6334405144694534,0.7218649517684887,0.7958199356913184,0.40836012861736337,0.40836012861736337,0.21114683815648444,0.6334405144694534,0.14437299035369774,0.7218649517684887,0.07958199356913183,0.7958199356913184,0.5376760832950542,0.6002459895262535,0.5464104053868796
+0,0,0.40836012861736337,0.6334405144694534,0.7218649517684887,0.7958199356913184,0.40836012861736337,0.40836012861736337,0.21114683815648444,0.6334405144694534,0.14437299035369774,0.7218649517684887,0.07958199356913183,0.7958199356913184,0.5376760832950542,0.6002459895262535,0.5464104053868796
+0,0,0.40836012861736337,0.6334405144694534,0.7218649517684887,0.7958199356913184,0.40836012861736337,0.40836012861736337,0.21114683815648444,0.6334405144694534,0.14437299035369774,0.7218649517684887,0.07958199356913183,0.7958199356913184,0.5376760832950542,0.6002459895262535,0.5464104053868796
+0,0,0.40836012861736337,0.6334405144694534,0.7218649517684887,0.7958199356913184,0.40836012861736337,0.40836012861736337,0.21114683815648444,0.6334405144694534,0.14437299035369774,0.7218649517684887,0.07958199356913183,0.7958199356913184,0.5376760832950542,0.6002459895262535,0.5464104053868796

Information-Retrieval_evaluation_test_results.csv

@@ -0,0 +1,5 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100
+0,0,0.43214556482183475,0.654030831437958,0.7556229466767753,0.8660601465756886,0.43214556482183475,0.3960224195819343,0.22778198972285402,0.6125801773830585,0.16254738438210767,0.7189633801460943,0.0964619661359616,0.8379727908348076,0.5708841273852633,0.6230490170650043,0.5550214647187748
+0,0,0.7132075471698113,0.9075471698113208,0.9641509433962264,0.9943396226415094,0.7132075471698113,0.7132075471698113,0.30251572327044024,0.9075471698113208,0.19283018867924526,0.9641509433962264,0.09943396226415095,0.9943396226415094,0.8202126385145252,0.863367502871466,0.8205632189982911
+0,0,0.7056603773584905,0.9037735849056604,0.9547169811320755,0.9943396226415094,0.7056603773584905,0.7056603773584905,0.3012578616352201,0.9037735849056604,0.1909433962264151,0.9547169811320755,0.09943396226415095,0.9943396226415094,0.8155480682839175,0.8597937744367032,0.8159563688254032
+0,0,0.7188679245283018,0.9150943396226415,0.9641509433962264,0.9943396226415094,0.7188679245283018,0.7188679245283018,0.30503144654088044,0.9150943396226415,0.19283018867924526,0.9641509433962264,0.09943396226415095,0.9943396226415094,0.8241719077568133,0.8663694271169878,0.8245394331184973

README.md

@@ -10,7 +10,7 @@ tags:
 
 ---
 
-# dell-research-harvard/lt-un-data-fine-industry-es
+# {MODEL_NAME}
 
 This is a [LinkTransformer](https://linktransformer.github.io/) model. At its core this model this is a sentence transformer model [sentence-transformers](https://www.SBERT.net) model- it just wraps around the class. 
 It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/linkage_un_data_es_fine_industry",
+  "_name_or_path": "hiiamsid/sentence_similarity_spanish_es",
   "architectures": [
     "BertModel"
   ],

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

pytorch_model.bin → test_data.pickle

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213e31b950d84bee8f77e75c3cd557932d9bc7dc76dcd03aba223c2e4f841a0f
-size 439467497
+oid sha256:258a6afd4ec0a61ce7ba4d9c64eaacba49cc242d396981ac6224dd00efc5c5e6
+size 68516

val_data.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1fb31aaa096101bf8cb0a320022e521d1d021cae177a11ea143ff78ecfaf71
+size 228390