Add model and update readme

.gitignore

@@ -0,0 +1,44 @@
+# Ignore Python cache and compiled files
+__pycache__/
+*.py[cod]
+*.pyo
+
+# Ignore logs
+*.log
+logs/
+*.out
+
+# Ignore prediction files (JSON format)
+*.json
+
+# Ignore environment and dependency files
+.env
+*.env
+*.venv
+venv/
+ENV/
+*.lock
+
+# Ignore Jupyter Notebook checkpoints
+.ipynb_checkpoints
+
+# Ignore temporary or backup files
+*.bak
+*.swp
+*.tmp
+
+# Ignore OS-specific files
+.DS_Store
+Thumbs.db
+
+# Ignore model checkpoint files (optional)
+checkpoint/
+*.ckpt
+
+# If using Hugging Face Model repository, don't ignore the following:
+!config.json
+!tokenizer_config.json
+!tokenizer.json
+!special_tokens_map.json
+!added_tokens.json
+!pytorch_model.bin

README.md

@@ -10,4 +10,37 @@ base_model:
 - microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
 pipeline_tag: token-classification
 library_name: transformers
----
+---
+
+# Fine-tuned NER Model for DiMB-RE
+
+## Model Description
+This is a fine-tuned **Named Entity Recognition (NER)** model based on the [BiomedNLP-BiomedBERT-base-uncased](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) model, specifically designed for token classification tasks in the biomedical domain. The model has been trained on the DiMB-RE dataset and is optimized to identify spans for 15 different entity type, as well as 13 different trigger type.
+
+<!-- ### Key Features:
+- **Language**: English
+- **Task**: Token classification for Named Entity Recognition (NER)
+- **Base Model**: BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
+- **Domains**: Biomedical, Clinical, Scientific -->
+
+## Performance
+The model has been evaluated on the DiMB-RE using the following metrics:
+- **NER** - P: 0.777, R: 0.745, F1: 0.760
+- **NER Relaxed** - P: 0.852, R: 0.788, F1: 0.819
+- **TRG** - P: 0.691, R: 0.631, F1: 0.660
+- **TRG Relaxed** - P: 0.742, R: 0.678, F1: 0.708
+
+## Citation
+If you use this model, please cite like below:
+
+'''bibtex
+@misc{hong2024dimbreminingscientificliterature,
+ title={DiMB-RE: Mining the Scientific Literature for Diet-Microbiome Associations}, 
+ author={Gibong Hong and Veronica Hindle and Nadine M. Veasley and Hannah D. Holscher and Halil Kilicoglu},
+ year={2024},
+ eprint={2409.19581},
+ archivePrefix={arXiv},
+ primaryClass={cs.CL},
+ url={https://arxiv.org/abs/2409.19581}, 
+}
+'''

added_tokens.json

@@ -0,0 +1,7 @@
+{
+ "[CLS]": 2,
+ "[MASK]": 4,
+ "[PAD]": 0,
+ "[SEP]": 3,
+ "[UNK]": 1
+}

config.json

@@ -0,0 +1,25 @@
+{
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+ "architectures": [
+ "BertForEntity"
+ ],
+ "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",
+ "torch_dtype": "float32",
+ "transformers_version": "4.34.0",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a9620511bb4dfe44e362ac1e7373f3c0cf6e1d4f17c27e9b8195de44ef529a
+size 440228250

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

@@ -0,0 +1,58 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [],
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_basic_tokenize": true,
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 1000000000000000019884624838656,
+ "never_split": null,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "unk_token": "[UNK]"
+}