RL-Verifier-Pitfalls
Collection
The collection for the Paper "Pitfalls of Rule- and Model-based Verifiers: A Case Study on Mathematical Reasoning."
•
7 items
•
Updated
This is the model checkpoint associated with the paper "Pitfalls of Rule- and Model-based Verifiers -- A Case Study on Mathematical Reasoning." The model is RL trained from the Qwen-2.5-7B base on the DeepScaleR dataset. Training employed a hybrid verification strategy combining the Huggingface Math Verifier and the opensource DeepSeek-R1-Distill-Qwen-1.5B.
- Downloads last month
- 5
Model tree for hkust-nlp/Qwen-2.5-7B-Verifier-R1-Qwen-1.5B
Base model
Qwen/Qwen2.5-7B