Upload TFBertForSequenceClassification

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: Sakonii/distilbert-base-nepali
+license: cc-by-nc-sa-4.0
+base_model: NepBERTa/NepBERTa
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,7 +13,7 @@ probably proofread and complete it, then remove this comment. -->
 
 # sakoni-distilBERT-NepSA
 
-This model is a fine-tuned version of [Sakonii/distilbert-base-nepali](https://huggingface.co/Sakonii/distilbert-base-nepali) on an unknown dataset.
+This model is a fine-tuned version of [NepBERTa/NepBERTa](https://huggingface.co/NepBERTa/NepBERTa) on an unknown dataset.
 It achieves the following results on the evaluation set:
 
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.32.0
+- Transformers 4.32.1
 - TensorFlow 2.12.0
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -1,34 +1,35 @@
 {
-  "_name_or_path": "Sakonii/distilbert-base-nepali",
-  "activation": "gelu",
+  "_name_or_path": "NepBERTa/NepBERTa",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "NEUTRAL",
     "1": "POSITIVE",
     "2": "NEGATIVE"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "NEGATIVE": 2,
     "NEUTRAL": 0,
     "POSITIVE": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_state": true,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.32.0",
-  "vocab_size": 24581
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30523
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:664af3c163d7181bcc65469422ad07932fb82591aa045c8e4cbd5ba4b946a289
-size 325224960
+oid sha256:e93e8210b6a6863e802f5558d3a9b6e68bb3e85ae1fce6c4d2ad0936a73e0c57
+size 532002416