initial commit

added_tokens.json

@@ -0,0 +1 @@
+{"[Q]": 250002, "[S]": 250003}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/layoutxlm-base",
+  "architectures": [
+    "LayoutLMv2ModelNoVisual"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "convert_sync_batchnorm": true,
+  "coordinate_size": 128,
+  "eos_token_id": 2,
+  "fast_qkv": false,
+  "gradient_checkpointing": false,
+  "has_relative_attention_bias": false,
+  "has_spatial_attention_bias": false,
+  "has_visual_segment_embedding": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "image_feature_pool_shape": [
+    7,
+    7,
+    256
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "shape_size": 128,
+  "transformers_version": "4.5.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bf6b3a37ccba7110adfbac92cdff2528bfd507af732a1a1a60adf64092d33d
+size 1114357083

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["[Q]", "[S]"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["[Q]", "[S]"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base"}