This mistral model was trained 2x faster with
Unsloth and Huggingface's TRL library.
model = AutoModelForCausalLM.from_pretrained("exillarml/fine_tuned_mistral_7b_dental_8_epoch_chatstyle_ml")
tokenizer = AutoTokenizer.from_pretrained("exillarml/fine_tuned_mistral_7b_dental_8_epoch_chatstyle_ml")