google
/

gemma-3-4b-it

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

Resources

View closed (23)

Does not works with bitsandbytes 4bit and 8bit

#27 opened about 1 year ago by

Pan&Scan is desable by default ?

#26 opened about 1 year ago by

Upload tokenizer.model

#23 opened about 1 year ago by

Having a hard time fine tuning with LoRA

#21 opened about 1 year ago by

Adding "vocab_size" to config.json

#20 opened about 1 year ago by

The checkpoint you are trying to load has model type `gemma3` but Transformers does not recognize this architecture.

#19 opened about 1 year ago by

getting key error while running inference for pipeline api given in "Usage section"

#18 opened about 1 year ago by

himanshu-bluebrain

How can I run the pipeline without the Image input?

#17 opened about 1 year ago by

AttributeError: 'HybridCache' object has no attribute 'float'

#15 opened about 1 year ago by

Not enough parameters in 4b config.json

#14 opened about 1 year ago by

AttributeError: 'Gemma3Config' object has no attribute 'vocab_size'

#13 opened about 1 year ago by

Add video inference

#12 opened about 1 year ago by

Local Installation Video and Testing - Step by Step

#10 opened about 1 year ago by

Question About Benchmark Version in README

#9 opened about 1 year ago by

Feedback: mildly disappointed there isn't 9B version

#8 opened about 1 year ago by