Upload ParaDetect LoRA model

README.md

@@ -1,3 +1,52 @@
----
-license: mit
----
+
+# DeBERTa-v3-Large Fine-tuned for AI Text Detection
+
+## Model Description
+This model is a fine-tuned version of microsoft/deberta-v3-large using LoRA (Low-Rank Adaptation) 
+for binary classification of human vs AI-generated text.
+
+## Training Details
+- **Base Model**: microsoft/deberta-v3-large
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
+- **Task**: Binary text classification (Human vs AI)
+- **Dataset**: AI Text Detection Pile (cleaned)
+- **Training Epochs**: 1.0
+- **Training Steps**: 4000
+- **Early Stopping**: Patience of 10 steps
+
+## Performance Metrics (Test Set)
+- **Accuracy**: 0.9931
+- **Precision (Weighted)**: 0.9931
+- **Recall (Weighted)**: 0.9931
+- **F1-score (Weighted)**: 0.9931
+
+## Class-wise Performance
+### Human Text (Class 0)
+- Precision: 0.9972
+- Recall: 0.9889
+- F1-score: 0.9930
+
+### AI Text (Class 1)
+- Precision: 0.9891
+- Recall: 0.9972
+- F1-score: 0.9931
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from peft import PeftModel
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained('/content/drive/MyDrive/Colab Notebooks/ParaDetect/models/deberta-v3-large-lora-final')
+base_model = AutoModelForSequenceClassification.from_pretrained('microsoft/deberta-v3-large')
+model = PeftModel.from_pretrained(base_model, '/content/drive/MyDrive/Colab Notebooks/ParaDetect/models/deberta-v3-large-lora-final')
+
+# Make predictions
+text = "Your text here"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+outputs = model(**inputs)
+prediction = torch.nn.functional.softmax(outputs.logits, dim=-1)
+```
+
+## Training Date
+2025-10-06 07:31:53

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-large",
+  "bias": "all",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "value_proj",
+    "dense",
+    "key_proj",
+    "output.dense"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05632189c39031f6a4b330d8852e68058e57d091866060469ec020d27e375a19
+size 114943888

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}