google/gemma-3-4b-it · Discussions

#46 opened 5 days ago by

sans07

gemma3-1b-it

#45 opened 11 days ago by

TAENNY

Explicitly include num_attention_heads and num_key_value_heads in text_config for Gemma3 4B

#44 opened 12 days ago by

ebsmothers

Deployment issues on sagemaker

#43 opened 19 days ago by

tychen6677

Please open-source Gemini 1.5 Flash

3

#42 opened 19 days ago by

drguolai

CUDA error: device-side assert triggered

#41 opened 19 days ago by

arshiasoori

Low GPU Utilization during inference?

#39 opened 21 days ago by

BagelBig

Object detection capabilities ?

#38 opened 21 days ago by

syrineM

SigLIP or SigLIP2 encoder?

#37 opened 27 days ago by

orrzohar

text-generation

#36 opened 27 days ago by

rakmik

I'm releasing the speech version of Gemma-3!

8

#35 opened 28 days ago by

junnei

Update README.md

#34 opened about 1 month ago by

sachin7yadava

Issue with vLLM Deployment of gemma-3-4b-it on Tesla T4 - No Output

#33 opened about 1 month ago by

twodaix

Batch processing on a GPU?

3

#32 opened about 1 month ago by

buckeye17-bah

Please release also Gemini Flash 1.5 weights.

#31 opened about 1 month ago by

ZeroWw

Finetuning script using HuggingFace

#30 opened about 1 month ago by

2U1

VRAM not freed during long generations (Gemma, max_new_tokens=3000)

#29 opened about 1 month ago by

Nessit

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

#28 opened about 1 month ago by

bajajrahul03

Does not works with bitsandbytes 4bit and 8bit

#27 opened about 1 month ago by

zokica

Pan&Scan is desable by default ?

3

#26 opened about 1 month ago by

Jack-HR-Red

Upload tokenizer.model

#23 opened about 1 month ago by

Nexesenex

Having a hard time fine tuning with LoRA

#21 opened about 1 month ago by

abcampbell

Adding "vocab_size" to config.json

#20 opened about 2 months ago by

nmysore

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

#19 opened about 2 months ago by

bedoonraj

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

#18 opened about 2 months ago by

himanshu-bluebrain

How can I run the pipeline without the Image input?

8

#17 opened about 2 months ago by

prakhaaaas

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

6

#15 opened about 2 months ago by

naruto-soop

Not enough parameters in 4b config.json

#14 opened about 2 months ago by

krammnic

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

7

8

#13 opened about 2 months ago by

MinecAnton209

Add video inference

#12 opened about 2 months ago by

merve

Local Installation Video and Testing - Step by Step

#10 opened about 2 months ago by

fahdmirzac

Question About Benchmark Version in README

#9 opened about 2 months ago by

lianghsun

Feedback: mildly disappointed there isn't 9B version