Upload 6 files

config.json

@@ -1,28 +1,82 @@
 {
-  "_name_or_path": "ap-mannion/drbert-umls-kgi",
-  "architectures": [
-    "CamembertModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 5,
-  "classifier_dropout": null,
-  "dim": 768,
-  "eos_token_id": 6,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
-  "model_type": "camembert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.27.4",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 32013
-}
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "float32",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": true,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "chunk_size_feed_forward": 0,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "CamembertForMaskedLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 5,
+    "pad_token_id": 1,
+    "eos_token_id": 6,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "Dr-BERT/DrBERT-4GB",
+    "transformers_version": "4.27.4",
+    "model_type": "camembert",
+    "vocab_size": 32013,
+    "hidden_size": 768,
+    "num_hidden_layers": 12,
+    "num_attention_heads": 12,
+    "hidden_act": "gelu",
+    "intermediate_size": 3072,
+    "hidden_dropout_prob": 0.1,
+    "attention_probs_dropout_prob": 0.1,
+    "max_position_embeddings": 514,
+    "type_vocab_size": 1,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-12,
+    "position_embedding_type": "absolute",
+    "use_cache": true,
+    "classifier_dropout": null,
+    "dim": 768
+}

kgi_specific_config.json

@@ -0,0 +1,29 @@
+{
+    "num_labels_link_pred": 6,
+    "link_pred_dropout": 0.1,
+    "num_labels_triple_clf": 2,
+    "triple_clf_dropout": 0.1,
+    "task_weight_coefficients": [
+        0.36271557267837584,
+        0.41185328196487253,
+        0.22543114535675166
+    ],
+    "n_tasks": 4,
+    "_clf_classes": [
+        32013,
+        6,
+        2,
+        32013
+    ],
+    "_module_list": [
+        "lm_head",
+        "link_classifier",
+        "triple_classifier",
+        "lm_head"
+    ],
+    "_nonzero_task_weight_coefficients": [
+        0.36271557267837584,
+        0.41185328196487253,
+        0.22543114535675166
+    ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ff0e52cce627131b812556941311b82d6a61ea244596ad2ed45343742e0ae8
-size 442580781
+oid sha256:b95685010bf3c97966d534fce3da73cb542eaf5a931d631d155b4d56793bfcc6
+size 548175458

special_tokens_map.json

@@ -1 +1,25 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}
+{
+  "additional_special_tokens": [
+    "[SY]",
+    "[RO]",
+    "[RQ]",
+    "[RN]",
+    "[RB]",
+    "[CHD]",
+    "[PAR]",
+    "[HREL]"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,25 @@
-{"name_or_path": "Dr-BERT/DrBERT-4GB", "model_max_length": 512, "model_input_names": ["input_ids", "attention_mask"], "can_save_slow_tokenizer": true}
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "./TokenizerFromScratchMLM/DrBERT_4GB_MLM/special_tokens_map.json",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}