Migrate to HF

dataseer-binary_bert/config.json

@@ -0,0 +1,19 @@
+{
+    "model_name": "dataseer-binary_bert",
+    "architecture": "bert",
+    "embeddings_name": null,
+    "char_embedding_size": 25,
+    "word_embedding_size": 0,
+    "dropout": 0.5,
+    "recurrent_dropout": 0.25,
+    "maxlen": 300,
+    "dense_size": 32,
+    "use_char_feature": false,
+    "list_classes": [
+        "dataset",
+        "no_dataset"
+    ],
+    "fold_number": 1,
+    "batch_size": 16,
+    "transformer_name": "allenai/scibert_scivocab_cased"
+}

dataseer-binary_bert/model_weights.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881e7efd5339f2264fe81dd2c5345d2870729ebcaa37d609b691554798090962
+size 440033696

dataseer-binary_bert/transformer-config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

dataseer-binary_bert/transformer-tokenizer/special_tokens_map.json

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

dataseer-binary_bert/transformer-tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_special_tokens": true, "max_length": 300, "add_prefix_space": true, "special_tokens_map_file": null, "name_or_path": "allenai/scibert_scivocab_cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

dataseer-first_bert/config.json

@@ -0,0 +1,42 @@
+{
+    "model_name": "dataseer-first_bert",
+    "architecture": "bert",
+    "embeddings_name": null,
+    "char_embedding_size": 25,
+    "word_embedding_size": 0,
+    "dropout": 0.5,
+    "recurrent_dropout": 0.25,
+    "maxlen": 300,
+    "dense_size": 32,
+    "use_char_feature": false,
+    "list_classes": [
+        "calorimetry",
+        "chromatography",
+        "coulombimetry data",
+        "densitometry",
+        "electrocardiograph",
+        "electroencephalogram",
+        "electromyography",
+        "electrooculography",
+        "electrophysiology",
+        "electroretinography",
+        "emission flame photometry",
+        "flow cytometry",
+        "genetic data",
+        "image",
+        "mass spectrometry",
+        "no_dataset",
+        "protein data",
+        "sound data",
+        "spectrometry",
+        "spectrum analysis",
+        "systematic review",
+        "tabular data",
+        "video recording",
+        "voltammetry data",
+        "x-ray diffraction data"
+    ],
+    "fold_number": 1,
+    "batch_size": 16,
+    "transformer_name": "allenai/scibert_scivocab_cased"
+}

dataseer-first_bert/model_weights.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428e552bf791ab71f7b699516ab9e403cc6dab1a77cf293dd7f2fc9214fd6541
+size 440104352

dataseer-first_bert/transformer-config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

dataseer-first_bert/transformer-tokenizer/special_tokens_map.json

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

dataseer-first_bert/transformer-tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_special_tokens": true, "max_length": 300, "add_prefix_space": true, "special_tokens_map_file": null, "name_or_path": "allenai/scibert_scivocab_cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

dataseer-reuse_bert/config.json

@@ -0,0 +1,19 @@
+{
+    "model_name": "dataseer-reuse_bert",
+    "architecture": "bert",
+    "embeddings_name": null,
+    "char_embedding_size": 25,
+    "word_embedding_size": 0,
+    "dropout": 0.5,
+    "recurrent_dropout": 0.25,
+    "maxlen": 300,
+    "dense_size": 32,
+    "use_char_feature": false,
+    "list_classes": [
+        "no_reuse",
+        "reuse"
+    ],
+    "fold_number": 1,
+    "batch_size": 16,
+    "transformer_name": "allenai/scibert_scivocab_cased"
+}

dataseer-reuse_bert/model_weights.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92337a7679870884c2cb7051199664b9691d19422f7b592e9deb4bed0ecdb01
+size 440033696

dataseer-reuse_bert/transformer-config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

dataseer-reuse_bert/transformer-tokenizer/special_tokens_map.json

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

dataseer-reuse_bert/transformer-tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_special_tokens": true, "max_length": 300, "add_prefix_space": true, "special_tokens_map_file": null, "name_or_path": "allenai/scibert_scivocab_cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}