google/gemma-3-27b-it · Discussions

#76 opened 17 days ago by

zarifhaikal01

Too much VRAM in vLLM

3

#75 opened 19 days ago by

cbrug

Gemma-3-27B-it not loading on multi-GPU setup

#74 opened 25 days ago by

glawyer

Passing pictures as arrays to the model (Pytorch or Numpy)

#73 opened 28 days ago by

artyomboyko

Update config.json

#71 opened about 1 month ago by

olegshulyakov

vllm and "gemma-3-27b-it" dont work

➕ 5

#70 opened about 1 month ago by

nastyafairypro

How to eval the video/image sequences?

3

#69 opened about 1 month ago by

lkllkl

Wrong context length limit for HuggingChat?

#68 opened about 2 months ago by

vesjolovam

Undesired output texts

#67 opened about 2 months ago by

Waisullah

Add reasoning capabilities for gemma 3

#66 opened about 2 months ago by

devopsML

Getting 401 unaauthorized when trying to use google/gemma-3-27b-it

#65 opened 2 months ago by

Milinddurugkar

Codificação de imagens no prompt

5

#64 opened 2 months ago by

areumtecnologia

pad output?

#63 opened 2 months ago by

Juniworld

Wrong answer by gemma3-27b-it : what is the difference betweem each: google/gemma-3-27b-it, google/gemma-3-27b-pt

#62 opened 2 months ago by

Waisullah

Example of a wrong answer from an Image analysis

#61 opened 2 months ago by

vince62s

Test using M1 Max (64G) and Word

#60 opened 2 months ago by

gptlocalhost

what does "it" in the model name represent?

#59 opened 2 months ago by

jdsouza

Update README.md

#58 opened 2 months ago by

denizzhansahin

Gemma3ForCausalLM has no `_prepare_4d_causal_attention_mask_with_cache_position` method defined in its base modeling class

#57 opened 3 months ago by

buckeye17-bah

Inference speed slow?

👍 2

#56 opened 3 months ago by

banank1989

Internal Server Error for url using vllm

#55 opened 3 months ago by

panyupj

Could not find the transformer layer class SiglipMultiheadAttentionPoolingHead in the model.

👍 1

#54 opened 3 months ago by

neilwu

Keeps repeating itself.

rdtfddgrffdgfdghfghdfujgdhgsf

#53 opened 3 months ago by

Why MLP so tiny but vision part of the model works quite well

#52 opened 3 months ago by

CCRss

Using google/gemma-3-4b-it as asssitant model for speculative decoding does not work

➕ 1

#51 opened 3 months ago by

sayambhu

Update README.md

#50 opened 3 months ago by

beita6969

SigLIP or SigLIP2 encoder?

12

#48 opened 3 months ago by

orrzohar

Updated model can't stop generation

#47 opened 3 months ago by

JackBAI

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

🚀 1

#46 opened 3 months ago by

junnei

Regarding the issue of errors in inference when converting to float16.

#45 opened 3 months ago by

LBJ6666

Please release the weights of Gemini 1.5 Flash

#43 opened 3 months ago by

ZeroWw

Template error: syntax error: Conversation roles must alternate user/assistant/user/assistant/

#42 opened 3 months ago by

stcat

Blank String in System Prompt causes Error - chat_prompt needs some fixes!

#41 opened 3 months ago by

calycekr

Specify maximum context length in config

➕ 1

#40 opened 3 months ago by

saattrupdan

Tokens generated per second

👍 1

3

#39 opened 3 months ago by

rameshch

Image tokenization

#38 opened 3 months ago by

Marbuel

TPU inference

#37 opened 3 months ago by

Arpit-Bansal

How to use the tokenizer of gemma-3

#36 opened 3 months ago by

rishav09

Is there a possiblity for Google to change the license type of Gemma3 or its next release?

🔥 4

#33 opened 3 months ago by

harisnaeem

/v1/chat/completions endpoint not working

🔥 2

#32 opened 3 months ago by

PremkumarChandak

please release AWQ version

🔥 3

#31 opened 3 months ago by

classdemo

evals (PT vs IT)

👍 1

#30 opened 3 months ago by

erichartford

Provide an access token

#29 opened 4 months ago by

Tirth09

Where are the QAT releases for Gemma 3?

➕ 1