Visual Question Answering
Safetensors
qwen3_vl
NemoVLM / README.md
Conkic's picture
Update README.md
d6b6c2e verified
|
Raw
History Blame Contribute Delete
421 Bytes
metadata
license: apache-2.0
base_model:
  - Qwen/Qwen3-VL-4B-Instruct
datasets:
  - InternRobotics/RoboInter-Data
pipeline_tag: visual-question-answering

Liaohe/NemoVLM

Model under development — please check back later.🤓

This a model after lora with qwen3-vl-4b-Instruct and the data including images and prompts

Following these specific steps yields better performance.

We will show them in our new article!