Transaction Details

{
  "type": "SET_VALUE",
  "ref": "/apps/knowledge/topics/courses/direct-preference-optimization-your-language-model--dpo-direct-preference-optimization/.info",
  "value": {
    "title": "Direct Preference Optimization: Your Language Model is Secretly a Reward Model —",
    "description": "DPO introduces a simple classification loss that directly optimizes language model policies on human preference data, eliminating the need for reinforcement learning while maintaining theoretical equivalence to the RLHF objective.",
    "created_at": 1779737530838,
    "created_by": "0x3521579BDe8FB987256a20A2b15E9FfA5Fb8d850"
  }
}

{
  "gas_amount_total": {
    "bandwidth": {
      "service": 0
    },
    "state": {
      "service": 0
    }
  },
  "gas_cost_total": 0,
  "code": 0,
  "bandwidth_gas_amount": 1,
  "gas_amount_charged": 0
}