Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+language: en
+license: mit
+library_name: transformers
+tags:
+- bert
+- scientific-text
+- embeddings
+- fine-tuned
+pipeline_tag: feature-extraction
+---
+
+# scibert-citation-model
+
+This model is a fine-tuned version of SciBERT specifically optimized for generating embeddings from scientific papers.
+
+## Model Details
+
+- **Base Model**: SciBERT (Scientific BERT)
+- **Fine-tuning Task**: Scientific paper understanding and embedding generation
+- **Language**: English (Scientific/Academic)
+- **Vocabulary**: Scientific vocabulary
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("your-username/scibert-citation-model")
+model = AutoModel.from_pretrained("your-username/scibert-citation-model")
+
+# Generate embeddings
+text = "Your scientific text here"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+with torch.no_grad():
+    outputs = model(**inputs)
+    embeddings = outputs.last_hidden_state[:, 0, :]  # [CLS] token embedding
+
+print(f"Embeddings shape: {embeddings.shape}")
+```
+
+## Performance
+
+Fine-tuned SciBert
+
+## Training Details
+
+- **Training Framework**: PyTorch/Transformers
+- **Fine-tuning Objective**: Scientific text understanding
+
+## Citation
+
+If you use this model in your research, please cite appropriately.

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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": "4.20.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090,
+  "_name_or_path": "allenai/scibert_scivocab_uncased",
+  "problem_type": "regression",
+  "num_labels": 1,
+  "id2label": {
+    "0": "citation_score"
+  },
+  "label2id": {
+    "citation_score": 0
+  }
+}

model_info_20250522_101851.txt

@@ -0,0 +1,18 @@
+SciBERT Citation Score Regression Model
+=====================================
+
+Base model: allenai/scibert_scivocab_uncased
+Training epochs: 4
+Batch size: 16
+Training date: 20250522_101851
+
+Test Results:
+mse: 0.08407380858564521
+rmse: 0.28995483887261686
+mae: 0.20648734952299239
+r2: 0.1967308853421441
+accuracy: 0.7746591820368885
+precision: 0.7403778866340098
+recall: 0.8470776621297038
+f1: 0.7901418969380134
+roc_auc: 0.8444197928624024

scibert_citation_score_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8830b3ec0b6a9a1f55b219f6b553d9d58c1936adce55bb52626929189b5fbd
+size 441862717

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
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

training_stats_20250522_101851.csv

@@ -0,0 +1,5 @@
+epoch,train_loss,val_loss,mse,rmse,mae,r2
+1,0.07147852029715084,0.06684045744343446,0.06685914278675237,0.25857134950870403,0.20464455017427158,0.36019672171960926
+2,0.056661207980126076,0.06664133808599451,0.06664208914254446,0.2581512911889934,0.1911871365339472,0.3622737993987213
+3,0.03796716657930858,0.07147907259133764,0.0714912685281264,0.2673785117172403,0.1930904997753184,0.31586996084278096
+4,0.02269730473143192,0.07996603017911696,0.07999330926759107,0.28283088457166605,0.1996500670638028,0.23451035450542967