init

README.md

@@ -0,0 +1,41 @@
+---
+datasets:
+- Hello-SimpleAI/HC3
+language:
+- en
+pipeline_tag: text-classification
+tags:
+- chatgpt
+---
+
+# Model Card for `Hello-SimpleAI/chatgpt-detector-roberta`
+
+This model is trained on **the mix of full-text and splitted sentences** of `answer`s from [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3).
+
+More details refer to [arxiv: 2301.07597](https://arxiv.org/abs/2301.07597) and Gtihub project [Hello-SimpleAI/chatgpt-comparison-detection](https://github.com/Hello-SimpleAI/chatgpt-comparison-detection).
+
+
+The base checkpoint is [roberta-base](https://huggingface.co/roberta-base).
+We train it with all [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3) data (without held-out) for 1 epoch.
+
+(1-epoch is consistent with the experiments in [our paper](https://arxiv.org/abs/2301.07597).)
+
+## Citation
+
+Checkout this papaer [arxiv: 2301.07597](https://arxiv.org/abs/2301.07597)
+
+```
+@article{guo-etal-2023-hc3,
+    title = "How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection",
+    author = "Guo, Biyang  and
+      Zhang, Xin  and
+      Wang, Ziyuan  and
+      Jiang, Minqi  and
+      Nie, Jinran  and
+      Ding, Yuxuan  and
+      Yue, Jianwei  and
+      Wu, Yupeng",
+    journal={arXiv preprint arxiv:2301.07597}
+    year = "2023",
+}
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "izhx/my-awesome-roberta",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Human",
+    "1": "ChatGPT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ChatGPT": 1,
+    "Human": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2c7f8f590b0acd7866b18d5561b9d27e82d31a3dc24a8909658d2a8149ed94
+size 498657517

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 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "izhx/my-awesome-roberta",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}