Ericu950

This is a fine-tuned version of the Llama-3.1-8B-Instruct model, specialized in assigning a place of origin to Greek inscriptions. On a test set of 2,870 unseen inscriptions, its top-1 predictions were, on average, correct in 75.0% of all cases; in 83.7% of all cases, the correcte place of origin was among the top-3 suggestions. See https://arxiv.org/abs/2409.13870. This model was finetuned on the Ericu950/Inscriptions1 dataset, which consists of Greek Inscriptions and their corresponding dates and geographical attributions sourced from PHI via https://github.com/sommerschield/iphi. To run the model on a GPU with large memory capacity, follow these steps: If you don’t have access to a larger GPU but want to try the model out, you can run it in a quantized format in Google Colab. The quality of the responses might deteriorate significantly. Follow these steps: Step 1: Connect to free GPU 1. Click Connect arrowdropdown near the top right of the notebook. 2. Select Change runtime type. 3. In the modal window, select T4 GPU as your hardware accelerator. 4. Click Save. 5. Click the Connect button to connect to your runtime. After some time, the button will present a green checkmark, along with RAM and disk usage graphs. This indicates that a server has successfully been created with your required hardware. Step 4: Run inference on an inscription of your choice