johannhartmann
/

mistral22b_orpo_de

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

This is a simple experiment using geman ORPO training for one epoch using qlora and unsloth on Vezora/Mistral-22B-v0.2

Downloads last month: 6

Safetensors

Model size

22.2B params

Tensor type

BF16

·

Datasets used to train johannhartmann/mistral22b_orpo_de