llava-hf
/

llava-v1.6-mistral-7b-hf

Image-Text-to-Text

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (16)

Fine Tuning results into ValueError: Number of image tokens in input_ids different from num_images.

#40 opened 1 day ago by

all the outputs from the llava-hf/llava-v1.6-mistral-7b-hf model are showing as <unk> when prompted with an image. kindly clarify if there is an issue or I’m doing something incorrectly?

#39 opened 7 days ago by

Potential ways to accelerate for image to text tasks?

#38 opened 19 days ago by

Processor config change leads to errors

#37 opened about 1 month ago by

Inference without images

#36 opened about 1 month ago by

Evaluation

#35 opened about 2 months ago by

Expanding inputs for image tokens in LLaVa-NeXT should be done in processing.

#34 opened 2 months ago by

Index out of range errors

#32 opened 3 months ago by

Can the model be used for commercial purposes?

#28 opened 5 months ago by

PLZ!😭When I run the template, I get the error“Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained."

#26 opened 6 months ago by

How to set the temperature

#25 opened 6 months ago by

Unable to test inference on SageMaker

#23 opened 6 months ago by

deploy on sagemaker

#20 opened 7 months ago by

Support for multiple images..

#19 opened 7 months ago by

New LLaVA-NeXT (2024-05 Release)

#18 opened 7 months ago by

Does this support PEFT API for fine-tuning?

#16 opened 8 months ago by

How to run on M3 MAX on macbook?

#13 opened 8 months ago by

works quite good actually using the Tag-Gui, but....

#12 opened 8 months ago by

Embedding Function

#11 opened 8 months ago by

Few Shot Example

#9 opened 9 months ago by

Several issues loading and using the model with transformers==4.39.2

#7 opened 9 months ago by

Does llava supports multi-gpu inference?

#6 opened 9 months ago by

Will you make a VIP version of llava 1.6 models?

#4 opened 9 months ago by

barleyspectacular

wrong padding token

#2 opened 10 months ago by