FloraBERT small v1.0

references:
github: https://github.com/gurveervirk/florabert/tree/main
kaggle dataset: https://www.kaggle.com/datasets/gsv001100/florabert-project

transformer/language-model/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "None",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "block_size": 258,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 258,
+  "max_seq_len": 1000,
+  "model_type": "roberta",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "test_size": 0.2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 5005
+}

transformer/language-model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66adfb2d9b014e34a81009a3f79b935bd6c2c18b204f601e947faa25281082c
+size 188710837

transformer/language-model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f9fe771c525a1261d04f43d5eedc68657c252a7856fa554ce442fba115bb5c
+size 4347

transformer/prediction-model/config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "/kaggle/working/florabert/models/transformer/language-model",
+  "alpha": 0.1,
+  "architectures": [
+    "RobertaForSequenceClassificationMeanPool"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "batch_norm": false,
+  "block_size": 258,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "end_token_idx": 1,
+  "eos_token_id": 2,
+  "freeze_base": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "log_offset": 1,
+  "max_position_embeddings": 258,
+  "max_seq_len": 1000,
+  "model_type": "roberta",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "output_hidden_states": true,
+  "output_mode": "regression",
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "start_token_idx": 0,
+  "test_size": 0.2,
+  "threshold": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 5005
+}

transformer/prediction-model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01035776add0f61859a66b7e13b8c2cb46bfa061fda86e181b48031840acc43e
+size 191071737

transformer/prediction-model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9900b0e7e66afa2ee2c161bff09d7a7d6a7d053ebc958a0af3c792b27978429
+size 4347