initial commit

README.md

@@ -0,0 +1,19 @@
+---
+language:
+- ar
+- de
+- en
+- es
+- fr
+- it
+- lv
+- nl
+- pt
+- zh
+library_name: transformers.js
+pipeline_tag: token-classification
+tags:
+- ONNX
+---
+This is a 02 quantized version of Davlan/distilbert-base-multilingual-cased-ner-hrl [https://huggingface.co/Davlan/distilbert-base-multilingual-cased-ner-hrl].
+It is Transformers.js compatible.

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert-base-multi-ner-onnx",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-DATE",
+    "2": "I-DATE",
+    "3": "B-PER",
+    "4": "I-PER",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-LOC",
+    "8": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-DATE": 1,
+    "B-LOC": 7,
+    "B-ORG": 5,
+    "B-PER": 3,
+    "I-DATE": 2,
+    "I-LOC": 8,
+    "I-ORG": 6,
+    "I-PER": 4,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.35.2",
+  "vocab_size": 119547
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321e064bed3e6d64119b67a570e6b85f6bce768849b221c23a30151216daba2d
+size 538990879

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0171f820ba30dcc0b37f94977d23e304972d5fb353bec0632e19858e8d9f392
+size 134986448

ort_config.json

@@ -0,0 +1,38 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {
+    "disable_attention": null,
+    "disable_attention_fusion": false,
+    "disable_bias_gelu": null,
+    "disable_bias_gelu_fusion": false,
+    "disable_bias_skip_layer_norm": null,
+    "disable_bias_skip_layer_norm_fusion": false,
+    "disable_embed_layer_norm": true,
+    "disable_embed_layer_norm_fusion": true,
+    "disable_gelu": null,
+    "disable_gelu_fusion": false,
+    "disable_group_norm_fusion": true,
+    "disable_layer_norm": null,
+    "disable_layer_norm_fusion": false,
+    "disable_packed_kv": true,
+    "disable_shape_inference": true,
+    "disable_skip_layer_norm": null,
+    "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,
+    "optimize_with_onnxruntime_only": null,
+    "use_mask_index": false,
+    "use_multi_head_attention": false,
+    "use_raw_attention_mask": false
+  },
+  "optimum_version": "1.13.1",
+  "quantization": {},
+  "transformers_version": "4.35.2",
+  "use_external_data_format": false
+}

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}