GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

image2text reasoning video-understanding vlm
1 Open Issue Need Help Last updated: Jul 3, 2025

Open Issues Need Help

View All on GitHub

AI Summary: The task requires resolving environment setup issues for the GLM-4.1V-9B-Thinking large language model. This involves installing specific commits of the transformers and vLLM libraries, along with other dependencies, using git, rather than pip, due to instability in the main branches. The vLLM installation may require C++ compilation, or a pre-compiled version can be used. The goal is to successfully set up the environment to run the model.

Complexity: 4/5
bug enhancement help wanted question

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

Python
#image2text#reasoning#video-understanding#vlm