OpenVisTool Model

This checkpoint is part of the model family released with OpenVisTool, an open recipe for synthesizing instructive visual tool-use trajectories. These models can interleave reasoning, visual tool calls, tool observations, and final answers to solve visually complex tasks.

The checkpoint is supervised fine-tuned on OpenVisTool-42K, which contains 42,048 tool-use trajectories. The release includes four checkpoints:

Checkpoint Base model
qwen3vl_8b_openvistool_42k Qwen3-VL-8B-Instruct
qwen35_4b_openvistool_42k Qwen3.5-4B
qwen35_9b_openvistool_42k Qwen3.5-9B
qwen35_27b_openvistool_42k Qwen3.5-27B
Downloads last month
6
Safetensors
Model size
27B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for LockOnN/qwen35_27b_openvistool_42k

Base model

Qwen/Qwen3.5-27B
Finetuned
(296)
this model

Dataset used to train LockOnN/qwen35_27b_openvistool_42k

Collection including LockOnN/qwen35_27b_openvistool_42k

Paper for LockOnN/qwen35_27b_openvistool_42k