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

.gitattributes

@@ -1,39 +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/90/bd/90bdce77eae35f764bb3a93efd2fefe20ecc09f5df9a10d2233a4f5389e3370c filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/7c/f1/7cf1e594ab2c0cdcfb5f197b181310a0ae3f6056d21c80ab97768f5c14819f64 filter=lfs diff=lfs merge=lfs -text
 .git/lfs/objects/88/5c/885c5c02114e5648a4ede851d2f307c0f52e2e9e4c6a5dc258f805a8853be456 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 +1,2 @@
+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
+0,0,0.8025751072961373,0.8991416309012875,0.9227467811158798,0.9420600858369099,0.8025751072961373,0.8025751072961373,0.2997138769670959,0.8991416309012875,0.18454935622317598,0.9227467811158798,0.094206008583691,0.9420600858369099,0.8505032699775186,0.8729551805151753,0.8524046985856795

Information-Retrieval_evaluation_test_results.csv

@@ -0,0 +1,2 @@
+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
+0,0,0.9517819706498952,0.9727463312368972,0.9832285115303984,0.9916142557651991,0.9517819706498952,0.9517819706498952,0.3242487770789657,0.9727463312368972,0.1966457023060797,0.9832285115303984,0.09916142557651993,0.9916142557651991,0.9636992113407209,0.9704057117956396,0.9639085701047351

README.md

@@ -9,7 +9,7 @@ tags:
 
 ---
 
-# dell-research-harvard/lt-mexicantrade4748
+# {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/lt-mexicantrade4748",
+  "_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 sha256:885c5c02114e5648a4ede851d2f307c0f52e2e9e4c6a5dc258f805a8853be456
-size 439467497
+oid sha256:64bfd962ab52d3a0d22029d0a4f9dac74afc558ea9d8bc6c619f02d39e4f5247
+size 89040

val_data.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e650c5c58a51fd8247227455016256465558c6bfd6a570f3538da1e708489cc3
+size 480802