fix: move config and tokenizer files out of LFS

These small JSON/text files were incorrectly tracked by LFS,
preventing HuggingFace from parsing model configuration.

.gitattributes

@@ -33,9 +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
-tokenizer.json filter=lfs diff=lfs merge=lfs -text
-vocab.txt filter=lfs diff=lfs merge=lfs -text
-config.json filter=lfs diff=lfs merge=lfs -text
 model.onnx filter=lfs diff=lfs merge=lfs -text
-special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
-tokenizer_config.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,3 +1,37 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2be5ac79eabc4e2544e512d41720bc9a479afed7e18622144842d4a463032888
-size 956
+{
+  "_name_or_path": "thejosango/nuha-mlm",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Not Online Violence",
+    "1": "Offensive Language",
+    "2": "Gender Based Violence"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Gender Based Violence": 2,
+    "Not Online Violence": 0,
+    "Offensive Language": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

special_tokens_map.json

@@ -1,3 +1,7 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3
-size 125
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1,3 +1,28 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5b87578b942af73f9ed0ebca8a1074d3954282ff64b751314c9d1886c390aa5a
-size 654
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "[بريد]",
+    "[مستخدم]",
+    "[رابط]"
+  ],
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "use_fast": true
+}