Add mllm_mapper
Use multimodal large language models (MLLMs) for image-text question answering tasks. Hyperparameters:
- max_new_tokens: the maximum number of new tokens generated by the model.
- sampling_params: sampling hyperparameters for text generation.
@Qirui-jiao Thanks for your contribution! Please carefully resolve conflicts and ensure correct OP counting.
This PR is marked as stale because there has been no activity for 21 days. Remove stale label or add new comments or this PR will be closed in 3 day.
Close this stale PR.
This PR is marked as stale because there has been no activity for 21 days. Remove stale label or add new comments or this PR will be closed in 3 day.
Close due to this PR was included in PR #550