Upload 11 files

.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
+Arabert-v2-base-ViT-B-16-SigLIP-512-2M.keras filter=lfs diff=lfs merge=lfs -text

Arabert-v2-base-ViT-B-16-SigLIP-512-2M.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75354778f6bbaa6ff600fbe8cdaf00ccec5001db26b8cea3542c794d5e6f02c8
+size 2707001140

Arabert-v2-base-ViT-B-16-SigLIP-512-2M.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360d4cf756dfc96ebbe9ccaf90f943e1d25a9ca7ca2e225cb7715893c5f62fbb
+size 2362569

README.md

@@ -0,0 +1 @@
+https://wandb.ai/uos_mlalp/mscoco_teacher_learning_full_data/runs/sub3hilv?workspace=user-malbarham

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/think3/Desktop/2. tf_testing_araclip/converting_tf_to_pt/bert-base-arabertv2-ViT-B-16-SigLIP-512-epoch-155-trained-2M",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c01dee1f8c01c2e377e5bc4e86e4b28483ed9b26f37b12989af4f8c146c3467
+size 540835571

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8580728937edf04b461f867103409c34981aed089c658508299619520157db7
+size 541040640

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "+ك",
+    "+كما",
+    "ك+",
+    "+وا",
+    "+ين",
+    "و+",
+    "+كن",
+    "+ان",
+    "+هم",
+    "+ة",
+    "[بريد]",
+    "لل+",
+    "+ي",
+    "+ت",
+    "+ن",
+    "س+",
+    "ل+",
+    "[مستخدم]",
+    "+كم",
+    "+ا",
+    "ب+",
+    "ف+",
+    "+نا",
+    "+ها",
+    "+ون",
+    "+هما",
+    "ال+",
+    "+ه",
+    "+هن",
+    "+ات",
+    "[رابط]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}