First model version for testing pipeline

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "</FAC>": 50013,
+  "</GPE>": 50005,
+  "</LOC>": 50011,
+  "</ORG>": 50009,
+  "</PER>": 50001,
+  "</VEH>": 50003,
+  "</WEA>": 50007,
+  "<FAC>": 50012,
+  "<GPE>": 50004,
+  "<LOC>": 50010,
+  "<ORG>": 50008,
+  "<PER>": 50000,
+  "<VEH>": 50002,
+  "<WEA>": 50006
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "lanwuwei/GigaBERT-v4-Arabic-and-English",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "ORG-AFF",
+    "2": "ART",
+    "3": "PHYS",
+    "4": "PART-WHOLE",
+    "5": "GEN-AFF",
+    "6": "PER-SOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ART": 2,
+    "GEN-AFF": 5,
+    "O": 0,
+    "ORG-AFF": 1,
+    "PART-WHOLE": 4,
+    "PER-SOC": 6,
+    "PHYS": 3
+  },
+  "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": "4.20.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50014
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277f1bc63e56cf1af6265f17764d03c3635d0b30328d16b8c4314186ae561f2a
+size 995776285

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef680d83f86c336d836d13bb5908b09eb0d7a542a93647e1a9585462d4b21a8a
+size 497900909

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d3b30a0b260d72b930e334ec49abd418af536d656456b030135e0d86e26e89
+size 14503

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<PER>",
+    "</PER>",
+    "<VEH>",
+    "</VEH>",
+    "<GPE>",
+    "</GPE>",
+    "<WEA>",
+    "</WEA>",
+    "<ORG>",
+    "</ORG>",
+    "<LOC>",
+    "</LOC>",
+    "<FAC>",
+    "</FAC>"
+  ],
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "lanwuwei/GigaBERT-v4-Arabic-and-English",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/srv/share5/ychen3411/huggingface_cache/c8a919731ad7551df88a744a8399190ea80a9961eaf96b8a59f86ef617e5144f.6a644b330fad284f98393c5832f71bce43df6855fa6ac7c9e44ed6271b708170",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}