Instructions to use bayesmaxxer/roberta-llm-classfier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bayesmaxxer/roberta-llm-classfier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="bayesmaxxer/roberta-llm-classfier")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("bayesmaxxer/roberta-llm-classfier") model = AutoModelForSequenceClassification.from_pretrained("bayesmaxxer/roberta-llm-classfier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
LLM-classifier
This model is a classifier that predicts which LLM wrote some text. It is based on Roberta and trained on a dataset of the outputs from three different LLMs (GPT-3.5, GPT-4o, and llama-3-sonar-small-32k-chat) on 440 prompts.
Note that this model was created as a fun test based on a tweet from Karpathy. In the future, I would like to improve/create a new model based on a bigger base model and with a larger training dataset. Not sure when that will happen though...
- Downloads last month
- 6