Edit model card

Harsha-Hermes-2.5-Mistral-7B

Harsha-Hermes-2.5-Mistral-7B is a DPO fine-tune of teknium/OpenHermes-2.5-Mistral-7B using the Intel/orca_dpo_pairs preference dataset and DPO notebook from Maxime Labonne.

Downloads last month
1,468
Safetensors
Model size
7.24B params
Tensor type
FP16
·