| license: other | |
| base_model: Qwen/Qwen3-VL-4B-Instruct | |
| tags: | |
| - vision-language | |
| - multimodal | |
| - evaluation | |
| # 0731 | |
| This repository contains a Hugging Face / vLLM-compatible multimodal model checkpoint. | |
| The checkpoint includes tokenizer, processor, generation config, model config, and model weights. | |