Q-Future/Q-Instruct
②[CVPR 2024] Low-level visual instruction tuning, with a 200K dataset and a model zoo for fine-tuned checkpoints.
PythonMIT
Issues
- 0
Image size
#23 opened by Nickyang4900 - 0
No eval_scripts in mPLUG-Owl-2
#22 opened by Evangeline98 - 0
- 0
ModuleNotFoundError: No module named 'boost_qa'
#20 opened by chenerg - 0
The demo failed
#19 opened by RollingWang - 1
About multi-turns conversations
#14 opened by yeppp27 - 1
Question on batch inference.
#17 opened by sentinel8b - 1
License
#18 opened by fakerybakery - 2
- 1
mPLUG-Owl Train Error: Attention mask shape
#15 opened by zxy110 - 0
- 4
About the evaluation code.
#12 opened by Yangr116 - 1
Q-Pathway Dataset
#11 opened by zxy110 - 0
how run thr Scorer API with local model
#10 opened by xu455255849 - 0
- 3
http api test
#8 opened by xu455255849 - 1
About the validation data of Table6
#7 opened by Yangr116 - 1
- 1
- 3
About IQA evaluation code
#4 opened by Qiulin-W - 2
- 1
Non initialized vision_tower weights when loading HF teowu/llava_v1.5_7b_qinstruct_preview_v0.1
#1 opened by theAdamColton