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
- 1