Model runs inference but returns empty output with run_VLM_hf.py on SpikingBrain-7B-VL

[Leonard-Yao]

Hi, When I test the SpikingBrain-7B-VL model using run_VLM_hf.py, the model runs normally and completes inference, but there is no output. The printed logs show that the generation finishes, but the decoded output is empty.

python3 run_VLM_hf.py
Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/sherry12334/SpikingBrain-7B-VL
You are using a model of type qwen2_5_vl to instantiate a model of type spikingbrain_vl. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 100%|██████████████████| 4/4 [00:07<00:00, 1.78s/it]
The image processor of type Qwen2VLImageProcessor is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with use_fast=False. Note that this behavior will be extended to all models in a future release.
You have video processor config saved in preprocessor.json file which is deprecated. Video processor configs should be saved in their own video_preprocessor.json file. You can rename the file or load and save the processor back which renames it automatically. Loading from preprocessor.json will be removed in v5.0.

==================================================

--- Example: LaTeX Extraction ---

How can I fix this issue?