license: mit | |
take the mistral inst-v02 model and run dpo on it, 6000 epoch. | |
take the mistral inst-v02 model and run dpo on it, 6000 epoch. | |
take the mistral inst-v02 model and run dpo on it, 6000 epoch. | |
take the mistral inst-v02 model and run dpo on it, 6000 epoch. | |
take the mistral inst-v02 model and run dpo on it, 6000 epoch. |