google/gemma-3-27b-it · Discussions

#70 opened 14 days ago by

nastyafairypro

How to eval the video/image sequences?

#69 opened 15 days ago by

lkllkl

Wrong context length limit for HuggingChat?

#68 opened 24 days ago by

vesjolovam

Undesired output texts

#67 opened 27 days ago by

Waisullah

Add reasoning capabilities for gemma 3

#66 opened 30 days ago by

devopsML

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

#65 opened about 1 month ago by

Milinddurugkar

Codificação de imagens no prompt

#64 opened about 1 month ago by

areumtecnologia

pad output?

#63 opened about 1 month 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 about 1 month ago by

Waisullah

Example of a wrong answer from an Image analysis

#61 opened about 1 month ago by

vince62s

Test using M1 Max (64G) and Word

#60 opened about 1 month ago by

gptlocalhost

what does "it" in the model name represent?

#59 opened about 2 months ago by

jdsouza

Update README.md

#58 opened about 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 about 2 months ago by

buckeye17-bah

Inference speed slow?

#56 opened about 2 months ago by

banank1989

Internal Server Error for url using vllm

#55 opened about 2 months ago by

panyupj

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

#54 opened about 2 months ago by

neilwu

Keeps repeating itself.

rdtfddgrffdgfdghfghdfujgdhgsf

#53 opened about 2 months ago by

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

#52 opened about 2 months ago by

CCRss

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

➕ 1

#51 opened 2 months ago by

sayambhu

Update README.md

#50 opened 2 months ago by

beita6969

SigLIP or SigLIP2 encoder?

7

#48 opened 2 months ago by

orrzohar

Updated model can't stop generation

#47 opened 2 months ago by

JackBAI

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

🚀 1

#46 opened 2 months ago by

junnei

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

#45 opened 2 months ago by

LBJ6666

Please release the weights of Gemini 1.5 Flash

#43 opened 2 months ago by

ZeroWw

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

#42 opened 2 months ago by

stcat

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

#41 opened 2 months ago by

calycekr

Specify maximum context length in config

➕ 1

#40 opened 2 months ago by

saattrupdan

Tokens generated per second

3

#39 opened 2 months ago by

rameshch

Image tokenization

#38 opened 2 months ago by

Marbuel

TPU inference

#37 opened 2 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)

#30 opened 3 months ago by

erichartford

Provide an access token

#29 opened 3 months ago by

Tirth09

Where are the QAT releases for Gemma 3?

➕ 1

#28 opened 3 months ago by

Downtown-Case

Hio

#27 opened 3 months ago by

Azeliox

CUDA error: CUBLAS_STATUS_NOT_SUPPORTED

#25 opened 3 months ago by

surak

Function calling with Gemma 3

5

#24 opened 3 months ago by

jasonisaac

can not run with vllm

7

#23 opened 3 months ago by

tankpigg

Simple questions too hard?

👍 2

8

#22 opened 3 months ago by

urtuuuu

ImportError: cannot import name 'Gemma3ForConditionalGeneration' from 'transformers'

#21 opened 3 months ago by

Sashv

awq version

👍 ❤️ 9

3

#20 opened 3 months ago by

rastegar

Adds `vocab_size` to config.json