Add new SentenceTransformer model.

README.md

@@ -6,7 +6,8 @@ tags:
 - feature-extraction
 - sentence-similarity
 - transformers
-
+datasets:
+- assin2
 ---
 
 # marquesafonso/albertina-sts
@@ -101,7 +102,7 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 10,
+    "epochs": 5,
     "evaluation_steps": 800,
     "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
     "max_grad_norm": 1,
@@ -111,7 +112,7 @@ Parameters of the fit()-Method:
     },
     "scheduler": "WarmupLinear",
     "steps_per_epoch": null,
-    "warmup_steps": 51,
+    "warmup_steps": 25,
     "weight_decay": 0.01
 }
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "PORTULAN/albertina-100m-portuguese-ptpt-encoder",
+  "_name_or_path": "marquesafonso/albertina-sts",
   "architectures": [
     "DebertaModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621a687aa7a9909a9d7ec65d2f69592c8dd91427aae35773c7b11382c5adf76a
+oid sha256:1f680335c2520653500d13083ae637696ad679d9174cf8730c4c7c6b94797f9a
 size 554429144

tokenizer_config.json

@@ -50,10 +50,17 @@
   "eos_token": "[SEP]",
   "errors": "replace",
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "tokenizer_class": "DebertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]",
   "vocab_type": "gpt2"
 }