Upload folder using huggingface_hub

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "lj408/PatClaimEval-Quality",
+  "architectures": [
+    "ContrastiveModel"
+  ],
+  "auto_map": {
+    "AutoModel": "modeling_contrastive.ContrastiveModel"
+  },
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265,
+  "license": "cc-by-nc-4.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90fe3d9634fa8ac8b91e3f4c27a0479110c10c99046278701418955aace1ae49
+size 594673468

modeling_contrastive.py

@@ -0,0 +1,31 @@
+from transformers import PreTrainedModel, LongformerConfig, LongformerModel
+import torch.nn as nn
+import torch
+
+class ContrastiveModel(PreTrainedModel):
+    
+    config_class = LongformerConfig
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.bert = LongformerModel._from_config(config)
+        self.fc = nn.Linear(config.hidden_size, 1)
+
+    def compute_score(self, input_ids, attention_mask):
+        outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
+        pooled_output = outputs.pooler_output  
+        score = self.fc(pooled_output).squeeze()  
+        score = torch.sigmoid(score)  
+        return score
+    
+    def score_pair(self, sentence_a, sentence_b, tokenizer, device, max_length=2048):
+
+        inputs = tokenizer(
+            sentence_a, sentence_b,
+            return_tensors="pt", padding="max_length", truncation=True,
+            max_length=max_length
+        ).to(device)
+
+        with torch.no_grad():
+            score = self.compute_score(inputs["input_ids"], inputs["attention_mask"])
+        return score.item()

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}