metadata
base_model:
- Qwen/Qwen2.5-VL-7B-Instruct
language:
- en
- zh
license: mit
metrics:
- accuracy
pipeline_tag: image-text-to-text
library_name: transformers
The CodeV-SFT model is used to continue training CodeV-RL, as described in the paper CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization.
For the code repository, please refer to: https://github.com/RenlyH/CodeV