Hugging Face's logo

blind-submission-artifacts
/
Vision-AutonoSearch-9B

Image-Text-to-Text
Safetensors
qwen3_5
conversational
Model card Files
xet
 Community

Vision-AutonoSearch-9B

A multimodal search agent for Visual Autonomous Investigation, fine-tuned from Qwen/Qwen3.5-9B. It accompanies an anonymous submission under review.

The model uses the system prompt, tools, and user messages in inference/:

  • system_prompt.txt: system prompt
  • tools.json: text_search, visual_search, visit
  • vai_user_instruction.txt: user message for image investigation
  • vqa_user_template.txt: user message for VQA
Downloads last month
28
Safetensors
Model size
9B params
Tensor type
BF16
·
Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for blind-submission-artifacts/Vision-AutonoSearch-9B

Base model

Qwen/Qwen3.5-9B-Base
Finetuned
Qwen/Qwen3.5-9B
Finetuned
(1,350)
this model
Quantizations
1 model