Upload AGS model from .pt checkpoint (contiguous tensors)

README.md

@@ -0,0 +1,30 @@
+---
+language:
+- ar
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- regression
+- arabic
+- dialectness
+- AGS
+base_model: CAMeL-Lab/bert-base-arabic-camelbert-mix
+license: apache-2.0
+---
+
+# Sanadshabann/AGS — Arabic Generality Score (AGS)
+
+Predicts a continuous **generality** score for a target word in context.  
+Wrap the target span with `[TGT] ... [/TGT]`.
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+tok = AutoTokenizer.from_pretrained("Sanadshabann/AGS", use_fast=True)
+model = AutoModelForSequenceClassification.from_pretrained("Sanadshabann/AGS").eval()
+text = "هذا مثال مع [TGT]الكلمة[/TGT] الهدف داخل الجملة."
+with torch.inference_mode():
+    score = model(**tok(text, return_tensors="pt", truncation=True)).logits.squeeze().item()
+print("generality:", float(score))
+Notes: problem_type=regression, num_labels=1. Evaluated with RMSE.

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[/TGT]": 30001,
+  "[TGT]": 30000
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-mix",
+  "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": "generality"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "generality": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b7f66a072d76f2cd3a20b89da402a20a3e4162c01aae36056fa6114258fda1
+size 436358124

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    "[TGT]",
+    "[/TGT]"
+  ],
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,79 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "[TGT]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "[/TGT]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[TGT]",
+    "[/TGT]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.json

@@ -0,0 +1,10 @@
+{
+  "exported_at_utc": "2025-11-02T12:37:21Z",
+  "task": "regression (generality score)",
+  "language": "ar",
+  "base_model": "CAMeL-Lab/bert-base-arabic-camelbert-mix",
+  "uses_special_tokens": [
+    "[TGT]",
+    "[/TGT]"
+  ]
+}