Add deberta-v3-small model

small/config.json

@@ -0,0 +1,85 @@
+{
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float16",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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": 3072,
+  "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": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0.0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.0",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

small/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3f11a0954b4890618a3a5676d0afb5a832171b76654e8f28493499b1018f53
+size 282653514

small/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

small/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f6e6c7570901aea91b2cc9d1146d12a26287f62362c13625f02669332f4a00
+size 5329