Add large PyTorch model

large/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

large/config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-country",
+    "2": "I-country",
+    "3": "B-state",
+    "4": "I-state",
+    "5": "B-verbatim_locality",
+    "6": "I-verbatim_locality",
+    "7": "B-verbatim_date",
+    "8": "I-verbatim_date",
+    "9": "B-verbatim_elevation",
+    "10": "I-verbatim_elevation",
+    "11": "B-verbatim_collectors",
+    "12": "I-verbatim_collectors",
+    "13": "B-verbatim_habitat",
+    "14": "I-verbatim_habitat",
+    "15": "B-verbatim_method",
+    "16": "I-verbatim_method",
+    "17": "B-verbatim_latitude",
+    "18": "I-verbatim_latitude",
+    "19": "B-verbatim_longitude",
+    "20": "I-verbatim_longitude"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-country": 1,
+    "B-state": 3,
+    "B-verbatim_collectors": 11,
+    "B-verbatim_date": 7,
+    "B-verbatim_elevation": 9,
+    "B-verbatim_habitat": 13,
+    "B-verbatim_latitude": 17,
+    "B-verbatim_locality": 5,
+    "B-verbatim_longitude": 19,
+    "B-verbatim_method": 15,
+    "I-country": 2,
+    "I-state": 4,
+    "I-verbatim_collectors": 12,
+    "I-verbatim_date": 8,
+    "I-verbatim_elevation": 10,
+    "I-verbatim_habitat": 14,
+    "I-verbatim_latitude": 18,
+    "I-verbatim_locality": 6,
+    "I-verbatim_longitude": 20,
+    "I-verbatim_method": 16,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

large/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f01c4de47b3f22c07d215e207fae38aba81cc7b065f57234fe38ca18914f05f
+size 1736183764

large/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

large/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

large/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "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": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

large/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efeca1e5f5d25afb73261ee340eb29b53bc6649d13f47c6b029844296d18845c
+size 5905