Upload 6 files

config.json

@@ -1 +1,81 @@
-{"_name_or_path": "ap-mannion/kgi-bert-m", "activation": "gelu", "architectures": ["DistilBertModel"], "attention_dropout": 0.15, "dim": 768, "dropout": 0.05, "hidden_dim": 3072, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 12, "n_layers": 12, "pad_token_id": 0, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "torch_dtype": "float32", "transformers_version": "4.27.4", "vocab_size": 50000}
+{
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "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": [
+        "DistilBertModel",
+        "DistilBertForMaskedLM"
+    ],
+    "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": null,
+    "pad_token_id": 0,
+    "eos_token_id": null,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/lustre/fswork/projects/rech/cuf/udk72sb/umls-kgi/model_configs/db-base",
+    "transformers_version": "4.27.4",
+    "vocab_size": 50010,
+    "max_position_embeddings": 512,
+    "sinusoidal_pos_embds": false,
+    "n_layers": 8,
+    "n_heads": 8,
+    "dim": 768,
+    "hidden_dim": 2048,
+    "dropout": 0.05,
+    "attention_dropout": 0.15,
+    "activation": "gelu",
+    "initializer_range": 0.02,
+    "qa_dropout": 0.1,
+    "seq_classif_dropout": 0.2,
+    "model_type": "distilbert",
+    "layer_norm_eps": 1e-12
+}

kgi_specific_config.json

@@ -0,0 +1,29 @@
+{
+    "num_labels_link_pred": 8,
+    "link_pred_dropout": 0.1,
+    "num_labels_triple_clf": 2,
+    "triple_clf_dropout": 0.1,
+    "task_weight_coefficients": [
+        0.37236131743576156,
+        0.3829458850250046,
+        0.24469279753923384
+    ],
+    "n_tasks": 4,
+    "_clf_classes": [
+        50010,
+        8,
+        2,
+        50010
+    ],
+    "_module_list": [
+        "lm_head",
+        "link_classifier",
+        "triple_classifier",
+        "lm_head"
+    ],
+    "_nonzero_task_weight_coefficients": [
+        0.37236131743576156,
+        0.3829458850250046,
+        0.24469279753923384
+    ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8648055449ce1f9cce99ecc4eb715eb7c582c97048a4d418e17c54c5a8166be4
-size 495459613
+oid sha256:d816f91d00bc3219ea104479db1344f2f5e1204fd2f7226b3f7a056ff16cd8b0
+size 492657362

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,11 @@
-{"name_or_path": "", "model_max_length": 1000000000000000019884624838656, "model_input_names": ["input_ids", "token_type_ids", "attention_mask"]}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 256,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "unk_token": "[UNK]"
+}