YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
OneReason-0.8B ORPO LoRA - Epoch 2
This repository contains one LoRA adapter checkpoint for the Kuaishou LLM4Rec competition.
Training
- Start: clean OneReason-0.8B competition base
- Method: direct ORPO LoRA from the first optimizer step
- Preference pairs: 32,705
- Completed epoch: 2
- LoRA rank / alpha / dropout: 32 / 32 / 0.0
- Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Files
adapter_model.safetensors: LoRA weightsadapter_config.json: the original training checkpoint config, preserved byte-for-byte
Evaluation status
The official constrained-beam competition evaluation has not been run for this adapter. This repository makes no performance claim.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support