GPT2 - Einstein EPFL Light

Quantized Fine-tuned version of well known GPT2 model using Llama3 Einstein dataset for the Supervised Fine Tuning (SFT) and a dataset composed of EPFL type questions (and more...) for Direct Preference Optimization (DPO).

Authors: Azza Jenane (contact), David Schroeter (contact) & Paulo Ribeiro (contact)

Downloads last month: 7

Safetensors

Model size

431M params

Tensor type

F32

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.