This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
hw1-hc3-detector is an open-weight model for text classification from Xun, released under Apache License 2.0. It has 23M parameters and a 512-token context. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Fine-tuned MiniLM classifier for the historical English HC3 benchmark. Dataset: Hello-SimpleAI/HC3, revision 4d0ff18143b5a7e1b1e79beb540c04549d1e59d3. One nonempty human/generated answer pair per eligible, deduplicated question.
Parameters23M
Context512
Weights90.9 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve hw1-hc3-detector (23M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.0 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 7, 2026.
hw1-hc3-detector on every accelerator the SAVRN Index prices, at every precision
Model Card
By Xun, published under apache-2.0, revision 1f6f6bc8de5e.
Fine-tuned MiniLM classifier for the historical English HC3 benchmark. Dataset: Hello-SimpleAI/HC3, revision 4d0ff18143b5a7e1b1e79beb540c04549d1e59d3. One nonempty human/generated answer pair per eligible, deduplicated question. Question-level 80/10/10 train/validation/test split with seed 42. AdamW, learning rate 2e-05, 5 epochs, batch size 32, maximum 256 tokens, dynamic padding. The baseline is logistic regression on frozen sentence embeddings. Performance measures this historical corpus, not current generators or unseen domains. Text is truncated at the maximum sequence length. Dataset style artifacts can influence predictions. Do not use this model as evidence of student misconduct.
Read Xun's full model card
HC3 human / ChatGPT answer classifier
Fine-tuned MiniLM classifier for the historical English HC3 benchmark. Labels: 0 = human, 1 = ChatGPT. Input is answer text only.
Evaluation
Baseline test accuracy: 0.844901 Fine-tuned test accuracy: 0.986932 Fine-tuned macro F1: 0.986930
Training and data
Dataset: Hello-SimpleAI/HC3, revision 4d0ff18143b5a7e1b1e79beb540c04549d1e59d3. One nonempty human/generated answer pair per eligible, deduplicated question. Question-level 80/10/10 train/validation/test split with seed 42. Split sizes: {'train': 37334, 'validation': 4666, 'test': 4668}. AdamW, learning rate 2e-05, 5 epochs, batch size 32, maximum 256 tokens, dynamic padding. The baseline is logistic regression on frozen sentence embeddings.
Limitations
Performance measures this historical corpus, not current generators or unseen domains. Text is truncated at the maximum sequence length. Dataset style artifacts can influence predictions. Do not use this model as evidence of student misconduct.
Inference
from transformers import pipeline
classifier = pipeline("text-classification", model="space-xun/hw1-hc3-detector")
print(classifier("An answer to classify.", truncation=True, max_length=256))
Configuration
- Architecture
- BertForSequenceClassification
- Context length (tokens)
- 512
- Layers
- 6
- Hidden size
- 384
- Feed-forward size
- 1,536
- Attention heads
- 12
- Vocabulary size
- 30,522
- Model type
- bert
Identity and Version
- Repository
- space-xun/hw1-hc3-detector
- Publisher
- Xun
- Task
- Text classification
- Modality
- Text
- Library
- Not stated by the source
- Parameters
- 23M parameters
- Languages
- en
- Revision
- 1f6f6bc8de5e4c66fa0c0a92314afc49257ed8b1
- First published
- 2026-10-01
- Last updated
- 2026-10-01
Files and Weights
6 files, 91.6 MB in total. The weights are 1 file totalling 90.9 MB in safetensors.
Weights1 file · 90.9 MB
Configuration1 file · 926 B
Tokenizer2 files · 712.1 KB
Documentation1 file · 1.4 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 90.9 MB | 1e740cd5faaf |
| config.json | Configuration | 926 B | — |
| README.md | Documentation | 1.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 711.5 KB | — |
| tokenizer_config.json | Tokenizer | 594 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 90.9 MB
Download from Xun
Released by Xun through its official repository on Hugging Face. Read the license.
Built From
- Derived from sentence-transformers/all-MiniLM-L6-v2
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 90.9 MB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About hw1-hc3-detector
How much GPU memory does hw1-hc3-detector need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (23M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run hw1-hc3-detector on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use hw1-hc3-detector commercially?
Yes. hw1-hc3-detector is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is hw1-hc3-detector's context length?
512 tokens, from the maximum position embeddings in its published configuration.
Similar Models
Baseline test accuracy: 84.49%; Fine-tuned test accuracy: 99.21%.
This is my fine-tuned model for Homework 1. The model classifies HC3 answers as: - 0: human - 1: ChatGPT sentence-transformers/all-MiniLM-L6-v2 I used the fixed dataset splits provided in the notebook.
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).