issues
search
amazon-science
/
mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
https://arxiv.org/abs/2302.00923
Apache License 2.0
3.77k
stars
309
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to use the test_step( ) method to predict upon a single question and image
#79
Wznnnnn
opened
1 month ago
0
Why can't I generate the correct rationales when I don't give the solution label to the validation set or test set?
#78
zhongfansun
closed
1 month ago
0
where is the code for a-okvqa?
#77
baiyuting
opened
3 months ago
0
Added resume ability.
#76
deb-kit2
opened
3 months ago
0
OverflowError: can't convert negative int to unsigned
#75
jackiecy
closed
6 months ago
1
Convert Eager Logging to Lazy Logging
#74
pixeeai
opened
6 months ago
2
How to use the mm-cot frame as a utility library through local LLM?
#73
dszpr
opened
8 months ago
1
Question on fine-tuning time
#72
JunseokLee42
opened
8 months ago
1
Can not train on GPU.
#71
Aierhaimian
closed
8 months ago
0
Where is the main_central.py
#70
SanghyeokSon
closed
8 months ago
0
OverflowError: out of range integral type conversion attempted
#69
1-sf
opened
9 months ago
3
Bump transformers from 4.30.0 to 4.36.0
#68
dependabot[bot]
opened
9 months ago
0
ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length. Perhaps your features (`image_ids` in this case) have excessive nesting (inputs type `list` where type `int` is expected).
#67
pavankale2709
opened
10 months ago
1
While running ‵extract_caption.py`, raise many garbled text. So will you put the models in `https://huggingface.co/Salesforce/instructblip-vicuna-7b/tree/main` the `llm` folder?
#66
HiccupFL
opened
10 months ago
1
Request for Release of Multimodal-CoT Large 738M Model
#65
Amyyyyeah
opened
10 months ago
3
"blip2_vicuna_instruct" can't find lead to nonetype
#64
HiccupFL
closed
10 months ago
1
Where is Gold Rationale from?
#63
jameszhou-gl
closed
11 months ago
1
[17:28:39] [Model]: Loading declare-lab/flan-alpaca-large...
#62
Sosycs
opened
1 year ago
3
ImportError: cannot import name 'Conv2dSame' from 'timm.models.layers' (unknown location)
#61
hunwenpinghao
opened
1 year ago
5
I can't find main_central.py.
#60
wuxi-dixi
opened
1 year ago
1
Question about two stages training?
#59
vhzy
opened
1 year ago
1
Update mm-cot v2 code & features & models
#58
cooelf
closed
1 year ago
0
How to train
#57
nacho00112
closed
1 year ago
0
Question: PC requirements
#56
nacho00112
closed
1 year ago
0
Implementation Mm-cot
#55
Billyroot
opened
1 year ago
1
Bump transformers from 4.21.1 to 4.30.0
#54
dependabot[bot]
closed
1 year ago
0
typo in utils.prompt line 104 and 106
#53
canornot
opened
1 year ago
1
How are the vision features generated here ? How to view detr.npy and clip.npy images
#52
1-sf
closed
1 year ago
1
Out of memory during eval but not train?
#51
jamiehz
opened
1 year ago
16
RuntimeError: shape '[8, 512, 768]' is invalid for input of size 614400
#50
romain-rsr
opened
1 year ago
1
Question about vision feature extractor
#49
YihanCao123
closed
11 months ago
2
D2L
#48
AIndres
opened
1 year ago
0
#The datasets of vision_features I can't fetch
#47
Chinenana
opened
1 year ago
3
Vision feature of questions that contains more than one image
#46
aiPenguin
opened
1 year ago
1
add extract_features
#45
cooelf
closed
1 year ago
0
requirements specification
#44
romain-rsr
opened
1 year ago
2
Use Caption?
#43
lonestar234028
closed
1 year ago
1
Can not repro the result
#42
lonestar234028
closed
1 year ago
1
killed during inference
#41
lonestar234028
closed
1 year ago
3
TypeError: linear(): argument 'input' (position 1) must be Tensor, not NoneType
#40
AIAnytime
opened
1 year ago
2
fix dependency issue with huggingface-hub and rich
#39
tonyhoo
closed
1 year ago
0
[Model] Z-loss + added rich
#38
AndreSlavescu
opened
1 year ago
0
Fakeddit inference
#37
Francesco-Ranieri
closed
1 year ago
0
KeyError: 'true_false'
#36
zcy1234321
opened
1 year ago
2
Question :The code to generate Vision Features
#35
roapple10
opened
1 year ago
5
run_inference update to solve issue #18
#34
igor-cheb
opened
1 year ago
0
Readme upd to solve issue #18
#33
igor-cheb
closed
1 year ago
0
CUDA out of memory during training
#32
pariskang
opened
1 year ago
3
Project Refactoring
#31
danparizher
closed
1 year ago
0
Branch 2
#30
shazilahmed17
closed
1 year ago
0
Next