allenai/reward-bench Issues
New Gemma-7b DPO Model
Closed 12Model Test Application
Closed 3Experiment with human vs gpt4 data
Updated 1Clean up / enhance DPO code
Closed 1Visualization requests
Closed 1Add New reward models
Closed 2Dataset v2 discussion & feedback
Updated 3`pad_token_id` issue
Closed 7New LLaMA-3 Seq. Classfier Model
Closed 6Generative RM
ClosedRename Starling 34B
ClosedCheck beaver cost model
Closed 1Add a new mistral RM model
Closed 1Check Qwen model
Closed 1Support Nous Mixtral
Closed 1Pref Sets updates
Closed 1Truncation of long sequences
Closed 1Best of N benchmark
Updated 2DATASET TRACKING
Closed 1