Gemma 3 270M: Compact model for hyper-efficient AI • Hacker News Board

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#41

Post by jgalt212 » Thu, Aug 14, 2025, 5:34 PM UTC

lucb1e wrote: post #38

ertgbnm wrote: post #21

Earlier quoted context omitted.

He may generate useless tokens but boy can he generate ALOT of tokens.

He? I know some Gemmas and it's distinctly a female name; is Gemma a boy's name where you're from?

Perhaps the poster we referring to Simon not Gemma.

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#42

Post by numpad0 » Thu, Aug 14, 2025, 5:35 PM UTC

marinhero wrote: post #14

simonw wrote: post #11

This model is a LOT of fun. It's absolutely tiny - just a 241MB download - and screamingly fast, and hallucinates wildly about almost everything. Here's one of dozens of results I got for "Generate an SVG of a pelican riding a bicycle". For this one it decided to write a poem: +-----------------------+ | Pelican Riding Bike | +-----------------------+ | This is the cat! | | He's got big wings and a happy tail. | | He…

Serious question but if it hallucinates about almost everything, what's the use case for it?

robotic parrots?

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#43

Post by ertgbnm » Thu, Aug 14, 2025, 5:37 PM UTC

lucb1e wrote: post #38

ertgbnm wrote: post #21

Earlier quoted context omitted.

He may generate useless tokens but boy can he generate ALOT of tokens.

He? I know some Gemmas and it's distinctly a female name; is Gemma a boy's name where you're from?

I don't really gender LLMs in my head in general. I guess Gemma is a female name. I only gendered it in the joke because I think it makes it funnier, especially since it's just "a little guy". I know they are giving gendered names to these models now but I think it's a bit weird to gender when interacting with them.

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#44

Post by VirusNewbie » Thu, Aug 14, 2025, 5:39 PM UTC

canyon289 wrote: post #2

Hi all, I built these models with a great team. They're available for download across the open model ecosystem so give them a try! I built these models with a great team and am thrilled to get them out to you. From our side we designed these models to be strong for their size out of the box, and with the goal you'll all finetune it for your use case. With the small size it'll fit on a wide range of hardware and cost…

hi Ravin, fellow Googler here. Curious if you can share here (or internally?) how these models were trained. Wondering if you face all the chaos the large models have during training?

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#45

Post by nico » Thu, Aug 14, 2025, 5:40 PM UTC

simonw wrote: post #11

This model is a LOT of fun. It's absolutely tiny - just a 241MB download - and screamingly fast, and hallucinates wildly about almost everything. Here's one of dozens of results I got for "Generate an SVG of a pelican riding a bicycle". For this one it decided to write a poem: +-----------------------+ | Pelican Riding Bike | +-----------------------+ | This is the cat! | | He's got big wings and a happy tail. | | He…

Could be interesting to use in a RAG setup and also finetuning it

For sure it won’t generate great svgs, but it might be a really good conversational model

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#46

Post by 0x00cl » Thu, Aug 14, 2025, 5:43 PM UTC

simonw wrote: post #11

This model is a LOT of fun. It's absolutely tiny - just a 241MB download - and screamingly fast, and hallucinates wildly about almost everything. Here's one of dozens of results I got for "Generate an SVG of a pelican riding a bicycle". For this one it decided to write a poem: +-----------------------+ | Pelican Riding Bike | +-----------------------+ | This is the cat! | | He's got big wings and a happy tail. | | He…

I see you are using ollamas ggufs. By default it will download Q4_0 quantization. Try `gemma3:270m-it-bf16` instead or you can also use unsloth ggufs `hf.co/unsloth/gemma-3-270m-it-GGUF:16`

You'll get better results.

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#47

Post by luckydata » Thu, Aug 14, 2025, 5:46 PM UTC

nico wrote: post #45

simonw wrote: post #11

This model is a LOT of fun. It's absolutely tiny - just a 241MB download - and screamingly fast, and hallucinates wildly about almost everything. Here's one of dozens of results I got for "Generate an SVG of a pelican riding a bicycle". For this one it decided to write a poem: +-----------------------+ | Pelican Riding Bike | +-----------------------+ | This is the cat! | | He's got big wings and a happy tail. | | He…

Could be interesting to use in a RAG setup and also finetuning it For sure it won’t generate great svgs, but it might be a really good conversational model

The article says it's not a good conversational model but can be used for data extraction and classification as two examples.

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#48

Post by TheJoeMan » Thu, Aug 14, 2025, 5:46 PM UTC

ertgbnm wrote: post #21

simonw wrote: post #11

This model is a LOT of fun. It's absolutely tiny - just a 241MB download - and screamingly fast, and hallucinates wildly about almost everything. Here's one of dozens of results I got for "Generate an SVG of a pelican riding a bicycle". For this one it decided to write a poem: +-----------------------+ | Pelican Riding Bike | +-----------------------+ | This is the cat! | | He's got big wings and a happy tail. | | He…

He may generate useless tokens but boy can he generate ALOT of tokens.

Can he draw an "alot" made of tokens? https://hyperboleandahalf.blogspot.com/2010/04/alot-is-bette...

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#49

Post by luckydata » Thu, Aug 14, 2025, 5:46 PM UTC

marinhero wrote: post #14

simonw wrote: post #11

This model is a LOT of fun. It's absolutely tiny - just a 241MB download - and screamingly fast, and hallucinates wildly about almost everything. Here's one of dozens of results I got for "Generate an SVG of a pelican riding a bicycle". For this one it decided to write a poem: +-----------------------+ | Pelican Riding Bike | +-----------------------+ | This is the cat! | | He's got big wings and a happy tail. | | He…

Serious question but if it hallucinates about almost everything, what's the use case for it?

Because that's not the job it was designed to do, and you would know by reading the article.

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#50

Post by roughly » Thu, Aug 14, 2025, 5:47 PM UTC

simonw wrote: post #11

This model is a LOT of fun. It's absolutely tiny - just a 241MB download - and screamingly fast, and hallucinates wildly about almost everything. Here's one of dozens of results I got for "Generate an SVG of a pelican riding a bicycle". For this one it decided to write a poem: +-----------------------+ | Pelican Riding Bike | +-----------------------+ | This is the cat! | | He's got big wings and a happy tail. | | He…

I audibly laughed at this one: https://gist.github.com/simonw/25e7b7afd6a63a2f15db48b3a51ec... where it generates a… poem? Song? And then proceeds to explain how each line contributes to the SVG, concluding with:

> This SVG code provides a clear and visually appealing representation of a pelican riding a bicycle in a scenic landscape.