add model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+vocab.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,32 @@
+---
+language:
+- am
+metrics:
+- accuracy
+- f1
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- Sentiment-Analysis
+- Hate-Speech
+- Finetuning-mBERT
+---
+
+
+
+**<h1>Hate-Speech-Detection-in-Amharic-Language-mBERT</h1>**
+
+This Hugging Face model card contains a machine learning model that uses fine-tuned mBERT to detect hate speech in Amharic language.
+The model was fine-tuned using the Hugging Face Trainer API.
+
+**<h1>Fine-Tuning</h1>**
+
+This model was created by finetuning the mBERT model for the downstream task of Hate speech detection for the Amharic language.
+The initial mBERT model used for finetuning is http://Davlan/bert-base-multilingual-cased-finetuned-amharic which was provided by Davlan on Huggingface.
+
+**<h1>Usage</h1>**
+
+You can use the model through the Hugging Face Transformers library, either by directly loading the model in your Python code
+ or by using the Hugging Face model hub.
+
+

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "amengemeda/amharic-hate-speech-detection-mBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}
+

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffef8b159b9d275f382b47b41da9eb5872c7a85abe0bfc75fa522074063c4559
+size 711489909

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a67cd5c26510fdd7e81ec75b25ef433d25f23fe8f1f198c01fe17280627e5b3
+size 1552337