Upload 7 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
+vocab.txt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,91 @@
+{
+  "_name_or_path": "dicta-il/dictabert",
+  "architectures": [
+    "BertForJointParsing"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "do_lex": true,
+  "do_morph": true,
+  "do_ner": true,
+  "do_prefix": true,
+  "do_syntax": true,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-ANG",
+    "1": "B-DUC",
+    "2": "B-EVE",
+    "3": "B-FAC",
+    "4": "B-GPE",
+    "5": "B-LOC",
+    "6": "B-ORG",
+    "7": "B-PER",
+    "8": "B-WOA",
+    "9": "B-INFORMAL",
+    "10": "B-MISC",
+    "11": "B-TIMEX",
+    "12": "B-TTL",
+    "13": "I-DUC",
+    "14": "I-EVE",
+    "15": "I-FAC",
+    "16": "I-GPE",
+    "17": "I-LOC",
+    "18": "I-ORG",
+    "19": "I-PER",
+    "20": "I-WOA",
+    "21": "I-ANG",
+    "22": "I-INFORMAL",
+    "23": "I-MISC",
+    "24": "I-TIMEX",
+    "25": "I-TTL",
+    "26": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANG": 0,
+    "B-DUC": 1,
+    "B-EVE": 2,
+    "B-FAC": 3,
+    "B-GPE": 4,
+    "B-INFORMAL": 9,
+    "B-LOC": 5,
+    "B-MISC": 10,
+    "B-ORG": 6,
+    "B-PER": 7,
+    "B-TIMEX": 11,
+    "B-TTL": 12,
+    "B-WOA": 8,
+    "I-ANG": 21,
+    "I-DUC": 13,
+    "I-EVE": 14,
+    "I-FAC": 15,
+    "I-GPE": 16,
+    "I-INFORMAL": 22,
+    "I-LOC": 17,
+    "I-MISC": 23,
+    "I-ORG": 18,
+    "I-PER": 19,
+    "I-TIMEX": 24,
+    "I-TTL": 25,
+    "I-WOA": 20,
+    "O": 26
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "newmodern": true,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "syntax_head_size": 128,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567156cdc5011b7ae8cfdce995c7771eb074f326ab2e30222bd6ec91e640c2c0
+size 744055504

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c044cfbef55940700248d15c10f48a79640605e756a19601b310ea8c92827e73
+size 744123513

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "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 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "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
+    },
+    "5": {
+      "content": "[BLANK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 sha256:0fb90bfa35244d26f0065d1fcd0b5becc3da3d44d616a7e2aacaf6320b9fa2d0
+size 1500244