Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "PLAIN",
+    "1": "VERBATIM",
+    "2": "CARDINAL",
+    "3": "TIME",
+    "4": "FRACTION",
+    "5": "LETTERS",
+    "6": "DIGIT",
+    "7": "MONEY",
+    "8": "TELEPHONE",
+    "9": "ORDINAL",
+    "10": "ELECTRONIC",
+    "11": "DECIMAL",
+    "12": "MEASURE",
+    "13": "DATE",
+    "14": "ABBREVIATION",
+    "15": "ADRESS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "ABBREVIATION": 14,
+    "ADRESS": 15,
+    "CARDINAL": 2,
+    "DATE": 13,
+    "DECIMAL": 11,
+    "DIGIT": 6,
+    "ELECTRONIC": 10,
+    "FRACTION": 4,
+    "LETTERS": 5,
+    "MEASURE": 12,
+    "MONEY": 7,
+    "ORDINAL": 9,
+    "PLAIN": 0,
+    "TELEPHONE": 8,
+    "TIME": 3,
+    "VERBATIM": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29564
+}

config.json

@@ -1,10 +1,10 @@
 {
-  "_name_or_path": "cointegrated/rubert-tiny",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "dtype": "float32",
   "emb_size": 312,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
@@ -55,8 +55,7 @@
   "num_hidden_layers": 3,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.57.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 29564

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777e5f2750c6e675c186d5b56fd11eac566e8e1a2a5be339d6b4c04f53cab535
+size 46781081

ort_config.json

@@ -0,0 +1,35 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {
+    "disable_attention_fusion": false,
+    "disable_bias_add_fusion": false,
+    "disable_bias_gelu_fusion": false,
+    "disable_bias_skip_layer_norm_fusion": false,
+    "disable_bias_splitgelu_fusion": false,
+    "disable_embed_layer_norm_fusion": true,
+    "disable_gelu_fusion": false,
+    "disable_group_norm_fusion": true,
+    "disable_layer_norm_fusion": false,
+    "disable_nhwc_conv": false,
+    "disable_packed_kv": true,
+    "disable_packed_qkv": false,
+    "disable_rotary_embeddings": false,
+    "disable_shape_inference": true,
+    "disable_skip_group_norm_fusion": false,
+    "disable_skip_layer_norm_fusion": false,
+    "enable_gelu_approximation": false,
+    "enable_gemm_fast_gelu_fusion": false,
+    "enable_transformers_specific_optimizations": true,
+    "fp16": false,
+    "no_attention_mask": false,
+    "optimization_level": 2,
+    "optimize_for_gpu": false,
+    "use_group_norm_channels_first": false,
+    "use_mask_index": false,
+    "use_multi_head_attention": false,
+    "use_raw_attention_mask": false
+  },
+  "quantization": {},
+  "use_external_data_format": false
+}

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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

@@ -1,15 +1,62 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "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
+    }
+  },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": false,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }