Add pipeline

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+trained_model/model.safetensors filter=lfs diff=lfs merge=lfs -text

bert_paper_classifier.py

@@ -0,0 +1,38 @@
+from transformers import Pipeline
+from collections.abc import Iterable
+import torch
+
+class SciBertPaperClassifierPipeline(Pipeline):
+    def _sanitize_parameters(self, **kwargs):
+        return {}, {}, {}
+
+    def preprocess(self, inputs):
+        if not isinstance(inputs, Iterable):
+            inputs = [inputs]
+        texts = [
+            f"AUTHORS: {' '.join(paper.authors) if isinstance(paper.authors, list) else paper.authors} "
+            f"TITLE: {paper.title} ABSTRACT: {paper.abstract}"
+            for paper in inputs
+        ]
+        inputs = self.tokenizer(
+            texts, truncation=True, padding=True, max_length=256, return_tensors="pt"
+        ).to(self.device)
+        return inputs
+
+    def _forward(self, model_inputs):
+        with torch.no_grad():
+            outputs = self.model(**model_inputs)
+        return outputs
+
+    def postprocess(self, model_outputs):
+        probs = torch.nn.functional.softmax(model_outputs.logits, dim=-1)
+        results = []
+        for prob in probs:
+            result = [
+                {self.model.config.id2label[label_idx]: score.item()}
+                for label_idx, score in enumerate(prob)
+            ]
+            results.append(result)
+        if 1 == len(results):
+            return results[0]
+        return results

trained_model/config.json

@@ -0,0 +1,103 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "acc-phys",
+    "1": "adap-org",
+    "2": "alg-geom",
+    "3": "ao-sci",
+    "4": "astro-ph",
+    "5": "atom-ph",
+    "6": "chao-dyn",
+    "7": "chem-ph",
+    "8": "cmp-lg",
+    "9": "comp-gas",
+    "10": "cond-mat",
+    "11": "cs",
+    "12": "dg-ga",
+    "13": "econ",
+    "14": "eess",
+    "15": "funct-an",
+    "16": "gr-qc",
+    "17": "hep-ex",
+    "18": "hep-lat",
+    "19": "hep-ph",
+    "20": "hep-th",
+    "21": "math",
+    "22": "math-ph",
+    "23": "mtrl-th",
+    "24": "nlin",
+    "25": "nucl-ex",
+    "26": "nucl-th",
+    "27": "patt-sol",
+    "28": "physics",
+    "29": "plasm-ph",
+    "30": "q-alg",
+    "31": "q-bio",
+    "32": "q-fin",
+    "33": "quant-ph",
+    "34": "solv-int",
+    "35": "stat",
+    "36": "supr-con"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acc-phys": 0,
+    "adap-org": 1,
+    "alg-geom": 2,
+    "ao-sci": 3,
+    "astro-ph": 4,
+    "atom-ph": 5,
+    "chao-dyn": 6,
+    "chem-ph": 7,
+    "cmp-lg": 8,
+    "comp-gas": 9,
+    "cond-mat": 10,
+    "cs": 11,
+    "dg-ga": 12,
+    "econ": 13,
+    "eess": 14,
+    "funct-an": 15,
+    "gr-qc": 16,
+    "hep-ex": 17,
+    "hep-lat": 18,
+    "hep-ph": 19,
+    "hep-th": 20,
+    "math": 21,
+    "math-ph": 22,
+    "mtrl-th": 23,
+    "nlin": 24,
+    "nucl-ex": 25,
+    "nucl-th": 26,
+    "patt-sol": 27,
+    "physics": 28,
+    "plasm-ph": 29,
+    "q-alg": 30,
+    "q-bio": 31,
+    "q-fin": 32,
+    "quant-ph": 33,
+    "solv-int": 34,
+    "stat": 35,
+    "supr-con": 36
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

trained_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012246932c7f834f77cb6ccc1fd6045e2ab13c386de6b8f67d7d6d4f90b734a8
+size 439811204

trained_model/special_tokens_map.json

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

trained_model/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]"
+}