lyuchenyang/Macaw-LLM
Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration
PythonApache-2.0
Issues
- 1
Data filtering step
#23 opened by chatsci - 0
- 4
- 1
Custom Dataset Finetuning
#34 opened by saransh03sharma - 0
Which tokenizer are you using?
#35 opened by sbkim052 - 2
missing file ”data/all_visual_names.json“
#3 opened by wanghao-cst - 0
- 0
Different LLM backbones?
#32 opened by kdu4108 - 0
Requirement Versions
#30 opened by memewizards - 3
Performance of the model
#22 opened by chatsci - 0
- 0
Deployment of Macaw-LLM
#28 opened by nahidalam - 0
How can i run train.sh on only one GPU?
#27 opened by X-G-Y - 0
please update the demo code?
#26 opened by dragen1860 - 1
Some weights of MM_LLMs were not initialized from the model checkpoint at ./mm_llms_trainer/ and are newly initialized:
#25 opened by BinZhu-ece - 5
Always have same response
#21 opened by kehanlu - 0
Using pad_token, but it is not set yet.
#24 opened by wanghao-cst - 1
- 1
What is the pad ID for tokenizer?
#19 opened by chatsci - 1
- 7
- 0
Paths for pretrained models
#16 opened by Muhammad4hmed - 1
which llama tokenizer to use?
#15 opened by chatsci - 1
Can I use this in Windows?
#14 opened by haorunze - 1
- 1
Model code error
#10 opened by Yimi81 - 1
Does it support langchain?
#8 opened by Aidenren1215 - 1
Resource problem?
#7 opened - 2
Missing License File
#11 opened by gokul-uf - 2
GPU Memory Requirement
#9 opened by SJY8460 - 1
Question about setting pad token
#6 opened by wanghao-cst - 1
Missing file "data_alp_hf.json"
#5 opened by wanghao-cst - 6
missing file 'data/avsd/avsd_train.json'
#4 opened by wanghao-cst - 1
Questions about Model
#1 opened by RitchieAlpha - 1
Call for paper
#2 opened by xingchensong