eric-ai-lab/MiniGPT-5
Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"
PythonApache-2.0
Issues
- 1
Question about garbled text
#46 opened by witnessai - 4
- 7
OSError: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.
#43 opened by Shimooth - 1
- 1
- 1
How can I input multi-images?
#39 opened by Hoyyyaard - 1
More pretrained model
#38 opened by Chuanqi-Zang - 1
Construction of dataset
#37 opened by Zeqiang-Lai - 4
OSError: Can't load tokenizer for 'E:\models--Vision-CAIR--vicuna-7b' but my local file exists
#36 opened by AnYiYa6 - 1
[BUG]Hello, there was an error (TypeError: unsupported operand type (s) for//: 'NoneType' and 'int') running Python playground.py
#32 opened by lckj2009 - 0
can not generate images
#42 opened by Alpha-X-95 - 1
vision encoder used in MiniGPT-5
#40 opened by dylanqyuan - 4
Problems about the implementation
#29 opened by Junction4Nako - 33
[BUG]Still not working, there is an error (TypeError: unsupported opera type (s) for//: 'NoneType' and 'int') when running Python playground. py
#35 opened by lckj2009 - 1
About the stage 1 pretraining
#33 opened by qy-NJU - 3
- 3
ABOUT GPU RAM
#31 opened by VTaPo - 1
About image comprehension task
#30 opened by MajorDavidZhang - 2
TypeError: Unexpected type <class 'NoneType'>
#28 opened by moonbaby9 - 6
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
#11 opened by lewisliuyi - 2
- 5
- 2
Bad text generation performance
#15 opened by McCarrtney - 1
Acknowledgement on LAVIS
#20 opened by dxli94 - 2
Enhancement about SDXL/ LLAMA-2
#19 opened by George0726 - 2
- 1
- 3
How to use lm loss for voken during training?
#14 opened by TiaoziLiao - 2
- 1
About the training time?
#12 opened by blue-blue272 - 6
Bad performance on example
#10 opened by Changhy1996 - 5
What kind of GPU does MiniGPT-5 need?
#5 opened by axbing - 1
How do you get the VIST dataset?
#1 opened by jacob-kang - 1
The GPT-5 from OpenAI hasn't been released yet, adopting such a name. Can the AI research community not be so impetuous?
#2 opened by JunZhan2000 - 1
requirement.py is missing
#3 opened by XGGNet