llava-hf/llava-1.5-7b-hf

Multiple Image Tokens

2

#60 opened 3 months ago by

rogergheser

question about multi-image support in llava-1.5-7b-hf

#59 opened 6 months ago by

laolaorkk

Update chat_template.jinja

#58 opened 6 months ago by

Leonardo6

Error Trying Inference

👀 3

1

#57 opened 7 months ago by

JPLabsAI

Request: DOI

#56 opened 7 months ago by

UdaraChamidu

No adapter_config.json

2

#55 opened 8 months ago by

OwlMoy

General finetuning Notebooks

#53 opened 10 months ago by

dburkhart07

probability tensor contains either `inf`, `nan` or element < 0

#50 opened 12 months ago by

hadibeyzaee

Regarding suda and bitsandbytes (pls HELP)

1

#49 opened about 1 year ago by

Anish-45

Can I use llava to finetune on my dataset for text-image classification? I have a image dataset with text information and it has multiple labels

#46 opened about 1 year ago by

Udbhav23

Are there any recommended codebases for evaluating llava-hf models?

👀 2

#43 opened about 1 year ago by

blameitonme1

The environment settings for fine-tuning the llava-1.5-7b-hf

👀 3

#42 opened about 1 year ago by

ssxc16

Suddenly getting an error while executing processor = AutoProcessor.from_pretrained( 'llava-hf/llava-1.5-7b-hf')

👍 10

11

#41 opened over 1 year ago by

Dipto084

How can I save or change the vision tower?

4

#40 opened over 1 year ago by

plll123

Is it possible to only input text in LLaVa model?

➕ 2

4

#38 opened over 1 year ago by

Tizzzzy

HELP

4

#37 opened over 1 year ago by

eunhaeleee

llava-1.5-7b-hf run on cpu

#35 opened over 1 year ago by

sdyy

is there difference between llava-hf/llava-1.5-7b-hf and liuhaotian/llava-v1.5-7b ???

3

#28 opened over 1 year ago by

hirasoooo

convert llava-v1.5-7b to liuhaotian/llava-v1.5-7b-hf format

22

#26 opened almost 2 years ago by deleted

Error during deploying llava-hf/llava-1.5-7b-hf using Amazon SageMaker

#25 opened almost 2 years ago by

dariahhlibova

Fine Tuning LLAVA for classification

1

#24 opened almost 2 years ago by

J812

How to fine-tune this model?

3

#23 opened almost 2 years ago by

LahalaHa

Hello, can you support the conversion of llava to onnx

1

#22 opened almost 2 years ago by

YinZiQi

ValueError: The input provided to the model are wrong.

2

#21 opened almost 2 years ago by

tkaintura

Consistency of results.

2

#20 opened almost 2 years ago by

areflesh

How to have a continuous conversation

6

#19 opened almost 2 years ago by

sucongCJS

image processing is different from the github version

3

#18 opened about 2 years ago by

enhaoz

Error while finetuning the model for ConditionalGeneration

2

#16 opened about 2 years ago by

alxenos

Why does it show `language_model = meta-llama/Llama-2-7b-hf` and not Vicuna?

6

#13 opened about 2 years ago by

HenningBlue

Error with finetuning

5

#12 opened about 2 years ago by

kshetrajna12

How would you finetune this model?

#11 opened about 2 years ago by

cgrimshawdev26

Why is `beam_search` not enabled in the samples?

2

#10 opened about 2 years ago by

floschne

Duration to generate a caption for 1 image

7

#9 opened about 2 years ago by

apapiu

Why is the result differ from liuhaotian/llava-v1.5-7b

5

#8 opened about 2 years ago by

wk21

transformers 4.35.3 is not released yet right ?

6

#1 opened about 2 years ago by

mohan007