google/gemma-4-31B-it · Discussions

#72 opened 3 days ago by

boyang-runllama

Will there be a small model for speculative decoding?

#71 opened 3 days ago by

Imagen 1 (2022) Should Be Open Sourced

👍 1

#70 opened 3 days ago by

Tralalabs

Question about tool-calling order in chat_template.jinja

#67 opened 4 days ago by

json0

gemma-4-31b-it unable to execute tool calling

#66 opened 5 days ago by

Naman2302

Do Gemma 4 models work well?

#65 opened 5 days ago by

fix: embed chat_template in tokenizer_config.json

#64 opened 7 days ago by

NERDDISCO

Infinite loop is not fixed even with Google API

👀 1

#63 opened 7 days ago by

alexcardo

Chat Template has a bug.

🤗 2

5

#62 opened 8 days ago by

Reithan

why print rightarrow

❤️👀 3

#61 opened 8 days ago by

wangtf-Kevin

Can anyone improve the model using the Rys methodology—by duplicating a block of layers?

9

#60 opened 9 days ago by

Strange behaviour of the tokenizer

#58 opened 10 days ago by

andercorral

Good Workflow

#57 opened 11 days ago by

anthoekfj

fix: function calling formatting in chat template

❤️ 2

#55 opened 11 days ago by

RyanMullins

Chat template is too complicated that even Gemma 4 itself has no idea how to parse it

#53 opened 11 days ago by

alexcardo

Hardware requirement

👍👀 3

13

#52 opened 12 days ago by

Charan01

Tokens per Image Parameter?

#51 opened 12 days ago by

buckeye17

Guys please add the MTP to this model

🔥 5

#50 opened 12 days ago by

Narutoouz

Will there be QAT models?

👍 10

#49 opened 12 days ago by

Gemma 4 E4B will be as encyclopedically well-read as the 12b model?

#48 opened 12 days ago by

Create BTS

#47 opened 12 days ago by deleted

brokersponsor

#46 opened 13 days ago by

Brokersponsor

Update README.md

#45 opened 13 days ago by

Brokersponsor

Qusetion about math_vision and mmmu_pro evaluation result

#44 opened 13 days ago by

JjjjjZzz

The Gemma 4 model is great. But...

👍 4

5

#43 opened 13 days ago by

suitup91

𝐎𝐍𝐋𝐘 𝐂𝐔𝐂𝐊𝐒 𝐀𝐍𝐃 𝐒𝐔𝐁𝐇𝐔𝐌𝐀𝐍𝐒 𝐅𝐎𝐋𝐋𝐎𝐖𝐒 𝐀𝚰 '𝐄𝐓𝐇𝚰𝐂𝐒' 𝐀𝐍𝐃 '𝐒𝐀𝐅𝐄𝐓𝐘'!

#42 opened 13 days ago by

Kickan

junk outputs

#41 opened 13 days ago by

rirv938

file size so big

#40 opened 13 days ago by

a9secondsleeper

How did you achieve such remarkable metrics?

🤝 2

6

#39 opened 13 days ago by

Rename README.md to README.md mmkk

#37 opened 13 days ago by

antromjjj

token masking and space_between_special_tokens during finetuning

#36 opened 13 days ago by

Darkhn

WHY IS NOT CODING WORK😤

👀🧠 5

#35 opened 14 days ago by

Drixpy

Featherless AI

#34 opened 14 days ago by

MarcosFRGames

Fantastic Model for Legal/English Language Use Cases

#33 opened 14 days ago by

md-1415

test it yourself

#32 opened 14 days ago by

rosspanda0

It can't edit code!!

7

#31 opened 15 days ago by

JoeSmith245

RuntimeError: FlashAttention forward only supports head dimension at most 256

👀 1

#30 opened 15 days ago by

badhon1512

Can you guys make a smaller dense?

9

#29 opened 15 days ago by

Nesy1

Missing 'reasoning' field in response when serving gemma-4-31B-it with vLLM

8

#28 opened 16 days ago by

Iann

Community resources for Gemma 4 deployment — mobile, local, and cloud paths

#27 opened 16 days ago by

Linncharm

trying

#26 opened 16 days ago by

tiiihzx

aav

#25 opened 16 days ago by

tiiihzx

a

#24 opened 16 days ago by

tiiihzx

Unable to view the model file the architecture!

#23 opened 16 days ago by

naren-1219

The first small model for honest conversation

👍 7

#22 opened 16 days ago by

ghostwithahat

Please, Google open-source the ancient model "Gemini 1.0 Pro". Please, devepoler comment and share with google.

👍 2

#21 opened 16 days ago by

Tralalabs

Fix Gemma4 `response_schema` regex to capture content after tool calls

👀 1

#19 opened 17 days ago by

qgallouedec

..but where's the bigger one?

👍 2

#18 opened 17 days ago by

jerryblunder

This model didn't release, it escaped 💀🫪

😎👍 7

#17 opened 17 days ago by

evewashere

🚀测评视频+OpenClaw中使用方式