llava-hf
/

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

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

Resources

View closed (21)

<\s> token in the chat template instead of the </s> EOS token

#41 opened over 1 year ago by

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

#40 opened over 1 year ago by deleted

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 over 1 year ago by

Potential ways to accelerate for image to text tasks?

#38 opened over 1 year ago by

Processor config change leads to errors

#37 opened over 1 year ago by

Inference without images

#36 opened over 1 year ago by

Evaluation

#35 opened over 1 year ago by

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

#34 opened over 1 year ago by

Index out of range errors

#32 opened over 1 year ago by

Can the model be used for commercial purposes?

#28 opened almost 2 years 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 almost 2 years ago by

How to set the temperature

#25 opened almost 2 years ago by

Unable to test inference on SageMaker

#23 opened almost 2 years ago by

deploy on sagemaker

#20 opened almost 2 years ago by

Support for multiple images..

#19 opened almost 2 years ago by

New LLaVA-NeXT (2024-05 Release)

#18 opened almost 2 years ago by

Does this support PEFT API for fine-tuning?

#16 opened about 2 years ago by

How to run on M3 MAX on macbook?

#13 opened about 2 years ago by

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

#12 opened about 2 years ago by

Embedding Function

#11 opened about 2 years ago by

Few Shot Example

#9 opened about 2 years ago by

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

#7 opened about 2 years ago by

Does llava supports multi-gpu inference?

#6 opened about 2 years ago by

Will you make a VIP version of llava 1.6 models?

#4 opened about 2 years ago by

barleyspectacular

wrong padding token

#2 opened about 2 years ago by