Add files using upload-large-folder tool

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,104 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-classification
+datasets:
+- rasbt/human-vs-ai-50k
+base_model: openai-community/gpt2
+base_model_relation: finetune
+metrics:
+- accuracy
+tags:
+- ai-text-detection
+- binary-classification
+- variable-position-readout
+---
+
+# GPT-2 Variable-Position AI-Text Detector
+
+This is a fully fine-tuned GPT-2 classifier for distinguishing human-written and AI-generated text. It uses a variable-position readout token immediately after the input text. The model was trained on [`rasbt/human-vs-ai-50k`](https://huggingface.co/datasets/rasbt/human-vs-ai-50k). Human-written text has label 0 and AI-generated text has label 1.
+
+The maximum context length is 1,024 tokens. Temperature scaling is applied during inference. The recorded best validation accuracy was 97.44%.
+
+ 
+## Download and use
+
+```bash
+hf download rasbt/ai-text-detector-gpt2-variable \
+  --local-dir models/ai-text-detector-gpt2-variable
+```
+
+```python
+import json
+from pathlib import Path
+
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+
+model_dir = Path("models/ai-text-detector-gpt2-variable")
+metadata = json.loads(
+    (model_dir / "detector-config.json").read_text(encoding="utf-8")
+)
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+model = AutoModelForSequenceClassification.from_pretrained(model_dir)
+model.eval()
+
+text = "Paste the text to classify here."
+text_ids = tokenizer(
+    text,
+    add_special_tokens=False,
+    truncation=True,
+    max_length=metadata["max_text_length"],
+)["input_ids"]
+
+if metadata["readout_position"] == "fixed":
+    padding_length = metadata["context_length"] - len(text_ids) - 1
+    input_ids = (
+        text_ids
+        + [tokenizer.pad_token_id] * padding_length
+        + [tokenizer.eos_token_id]
+    )
+    attention_mask = [1] * len(text_ids) + [0] * padding_length + [1]
+else:
+    input_ids = text_ids + [tokenizer.eos_token_id]
+    attention_mask = [1] * len(input_ids)
+
+inputs = {
+    "input_ids": torch.tensor([input_ids]),
+    "attention_mask": torch.tensor([attention_mask]),
+}
+with torch.inference_mode():
+    logits = model(**inputs).logits / metadata["temperature"]
+    probabilities = logits.float().softmax(dim=-1)
+
+ai_index = metadata["label_mapping"]["ai"]
+ai_probability = probabilities[0, ai_index].item()
+print({"score": round(100 * ai_probability, 4)})
+```
+
+ 
+## Test-set confusion matrix
+
+![GPT-2 variable-position test-set confusion matrix](figures/confusion-matrix.svg)
+
+`detector-config.json` contains the readout, calibration, and training metadata. The recommended inference implementation is provided in the [`rasbt/ai-detector`](https://github.com/rasbt/ai-detector) repository because classification requires selecting the configured readout position.
+
+ 
+## Related models
+
+- [TF-IDF logistic regression](https://huggingface.co/rasbt/ai-text-detector-logreg)
+- [DistilBERT](https://huggingface.co/rasbt/ai-text-detector-distilbert)
+- [DistilBERT with LoRA](https://huggingface.co/rasbt/ai-text-detector-distilbert-lora)
+- [DistilBERT with MiCA](https://huggingface.co/rasbt/ai-text-detector-distilbert-mica)
+- [ModernBERT](https://huggingface.co/rasbt/ai-text-detector-modernbert)
+- [GPT-2 with a fixed-position readout](https://huggingface.co/rasbt/ai-text-detector-gpt2-fixed)
+- [Qwen3 0.6B with a fixed-position readout](https://huggingface.co/rasbt/ai-text-detector-qwen3-0.6b-fixed)
+- [Qwen3 0.6B with a variable-position readout](https://huggingface.co/rasbt/ai-text-detector-qwen3-0.6b-variable)
+
+ 
+## Limitations
+
+Performance may change for text from generators, domains, languages, and editing workflows not represented in the training set. Short or partly AI-assisted text may also be harder to classify. The score should not be treated as definitive evidence that a person did or did not write a text.

config.json

@@ -0,0 +1,50 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "HUMAN",
+    "1": "AI"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "AI": 1,
+    "HUMAN": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50257,
+  "problem_type": "single_label_classification",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vocab_size": 50258
+}

detector-config.json

@@ -0,0 +1,33 @@
+{
+  "dataset": "rasbt/human-vs-ai-50k",
+  "base_model": "openai-community/gpt2",
+  "label_mapping": {
+    "human": 0,
+    "ai": 1
+  },
+  "readout_position": "variable",
+  "attention_implementation": "flash_attention_2",
+  "model_dtype": "torch.bfloat16",
+  "readout_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "context_length": 1024,
+  "max_text_length": 1023,
+  "decision_threshold": 0.5,
+  "calibration": "temperature scaling",
+  "temperature": 2.770064980432574,
+  "best_validation_accuracy": 0.9744346116027532,
+  "best_checkpoint": "checkpoints-gpt2-variable-position/checkpoint-2535",
+  "trainable_parameters": 124442112,
+  "per_device_train_batch_size": 16,
+  "gradient_accumulation_steps": 1,
+  "training_runtime_seconds": 1540.0496,
+  "random_state": 17,
+  "python_version": "3.12.3",
+  "package_versions": {
+    "datasets": "4.1.0",
+    "numpy": "2.5.1",
+    "scikit-learn": "1.7.1",
+    "torch": "2.13.0",
+    "transformers": "5.14.1"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df896fa694ba9c38cee25b31fb00c506ea000a355666b89feffddb248a21e78
+size 248899336

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}