3 fun Gemma project ideas

JUL 10, 2024
Ju-yeong Ji Gemma DevRel

Gemma is a family of open models built from the same research and technology used to create the Gemini models. The family currently includes Gemma, CodeGemma, PaliGemma, and RecurrentGemma. Collectively, the models are capable of performing a wide range of tasks, including text generation, code completion and generation, many vision-language tasks, and can run on various devices from edge to desktop to cloud. You can go even further and fine-tune Gemma models to suit your specific needs.

Gemma is built for the open community of developers and researchers powering AI innovation. You can explore more about Gemma and access quickstart guide on ai.google.dev/gemma

In this blog post, let's explore 3 fun project ideas and how to use Gemma models to create them:

  • Translating old Korean language

  • Game design brainstorming

  • A letter to Santa

#1. Translator of old Korean literature

Project Description

The Korean alphabet, or Hangul, has undergone changes over time, resulting in several letters no longer used in modern Korean. These obsolete letters include:

  1. ㆍ (Arae-a): This dot vowel represents a short 'a' sound.

2. ㆆ (Yeorin-hieut): Pronounced as a 'light h,' akin to a softer version of the English 'h.'

3. ㅿ (Bansiot): Represents the 'z' sound.

4. ㆁ (Yet-ieung): A velar nasal sound comparable to 'ng' in the word 'sing.'

For native Korean speakers, reading older literature presents a challenge due to the utilization of now-obsolete letters. Early Hangul lacked spaces between words, further complicating readability. In contrast, modern Hangul employs spaces, consistent with most alphabetic systems.

Gemma's capabilities enable the creation of a translator that assists in comprehending and bridging the divide between contemporary and archaic Korean. SentencePiece serves as the foundation for Gemma's tokenizer. In contrast to conventional tokenizers, which heavily rely on language-specific guidelines or predefined dictionaries, SentencePiece undergoes training directly on raw text data. Consequently, it becomes independent of any specific language and adaptable to various forms of text data.

What you will need


To simplify the task, we will adopt the following structure for fine-tuning the model. The model will generate contemporary Korean text based on the user's input in Early Hangul.

Korean text means, In the fifteenth year of the reign of King Sejong of Joseon, there was a prime minister outside Honghoemun Gate.
NOTE: Korean text means, In the fifteenth year of the reign of King Sejong of Joseon, there was a prime minister outside Honghoemun Gate.

Instruction-tuned (IT) models are trained with a specific formatter. Note that the control tokens are tokenized in a single token in the following manner:

Instruction-tuned (IT) models being trained with a specific formatter, with control tokens being tokenized in a single token

For model training, we will use “Hong Gildong jeon”, a Joseon Dynasty-era Korean novel.

To assess the model’s output quality, we will use text from outside the training datasets, specifically the classic Korean novel “Suk Yeong Nang Ja jeon” by an unknown author.

Inference before fine tuning

The model has no capability to translate Early Hangul.

Inference before fine tuning

LoRA Fine-tuning

After fine-tuning, responses follow the instruction, and it generates contemporary Korean text based on the Early Hangul text.

Model generated contemporary Korean text

For your reference, please see the following text, which has been translated by a human:

금두꺼비가 품에 드는 게 보였으니 얼마 안 있어 자식을 낳을 것입니다.

하였다. 과연 그 달부터 잉태하여 십삭이 차니

Note: Korean text means, “I saw a golden toad in her arms, so it won’t be long before she gives birth to a child.” Indeed, she conceived from that month and was ten months old.

And here's another output.

Model generated contemporary Korean text - example 2

And the translation by a human below:

이 때는 사월 초파일이었다. 이날 밤에 오색구름이 집을 두르고 향내 진동하며 선녀 한 쌍이 촉을 들고 들어와 김생더러 말하기를,

Note: Korean text means, At this time, it was the 8th of April. On this night, with five-colored clouds surrounding the house and the scent of incense vibrating, a pair of fairies came in holding candles and said to Kim Saeng,

Although the translation is not flawless, it provides a decent initial draft. The results are remarkable, considering that the datasets are limited to a single book. Enhancing the diversity of data sources will likely improve the translation quality.

Once you fine tune the model, you can simply publish it to Kaggle and Hugging Face.

Below is an example.

# Save the finetuned model

# Upload the model variant on Kaggle
kaggle_uri = "kaggle://my_kaggle_username/gemma-ko/keras/old-korean-translator"
keras_nlp.upload_preset(kaggle_uri, "./old-korean-translator")

Expansion Idea

To achieve similar tasks, you can replicate the same structure. Below are some examples:

  • American English <-> British English datasets

Various everyday objects and concepts have different names depending on the region. For example, in American English (AmE), people use terms like "elevator," "truck," "cookie," and "french fries," while in British English (BrE), the equivalent words are "lift," "lorry," "biscuit," and "chips," respectively.

Apart from vocabulary differences, spelling variations also exist. For instance, in AmE, words ending in "-or" are often spelled with "-our" in BrE. Examples include "color" (AmE) and "colour" (BrE), or "humor" (AmE) and "humour" (BrE).

Another spelling variation is the "-ize" versus "-ise" distinction. In AmE, words like "organize" and "realize" are commonly spelled with a "z," whereas in BrE, the preferred spelling is "organise" and "realise," using an "s" instead.

With the help of AI tools like Gemma, it is possible to create a style transfer from one English to another, allowing seamless transitions between American and British English writing styles.

  • Kansai-ben datasets

In the Kansai region of Japan, there is a distinct group of dialects known as Kansai-ben. Compared to the standard Japanese language, native speakers perceive Kansai-ben as being both more melodic and harsher in its pronunciation and intonation.

Utilizing the Gemma's capabilities, you can create a dialect translator by preparing a substantial quantity of Kansai-ben datasets.

#2. Game design brainstorming

Project Description

With Gemma as your trusty companion, you can embark on a journey to create a captivating game. It all starts with a simple one-sentence pitch that serves as the foundation of your game's concept. Gemma will skillfully guide you in fleshing out the game's concept, crafting intricate main characters, and writing a captivating main story that will immerse players in your game's world.

What you will need


Starting with writing a core concept, one-sentence pitch of your game, like below:

Example of a one-sentence gameplay pitch

Gemma can add more details based on your pitch.

Input : “Elaborate about this game with the given core concept below.\n{pitch}”

Example Output :

Example of Gemma output elaborating on the gameplay idea provided in an earlier prompt

Input : “Design main characters”

Example Output :

Gemma example output for prompt "Design main characters"

Input : “Design villain characters”

Example Output :

Example of Gemma output for prompt "design villain characters"

Input : “Write the main story of this game with an introduction, development, turn, and conclusion.”

Example Output :

Example of Gemma output for prompt requesting a main story with an introduction, development, turn, and conclusion

Expansion Idea

By modifying the prompt, you can get a similar companion for almost any type of creative content.

Marketing Phrase

Pitch : “A new steam-powered toothbrush”

Input : “Generate a marketing phrase for the new product below.\n{pitch}”

Example Output :

Example of Gemma output for prompt "Generate a marketing phrase for the new product below.\n{pitch}""

Florist Ideas

Pitch : “Universe and shooting stars”

Input : “Generate a florist idea inspired by the concept below, along with suggestions for suitable flowers.\n{pitch}”

Example Output :

Example of Gemma output for prompt requesting a florist idea based on a provided prompt

Food Recipe

Pitch : “Cyberpunk Kraken”

Input : “Generate a cooking recipe with the concept below.\n{pitch}”

Example Output :

Example of Gemma output for prompt requesting a recipe based on a provided prompt

#3. The magic of Santa’s mailbox

Project Description

The traditional method of sending letters to Santa can be limited and impersonal. Children often have to wait weeks or even months for a response, and their letters may not be as detailed or interactive as they would like.

In this project, we will use Gemma, running on a Raspberry Pi, to compose magical letters from Santa using the power of a large language model.

What you will need


  • A raspberry Pi 4 computer with 8GB RAM


Text generation

A. You can write your own C++ application with libgemma.

You can write your own C++ application with libgemma.

Use the prompt below to instruct the model

Example of a prompt to instruct a Gemma model to write  a letter to Santa

B. Or use this simple c++ app for testing.

Before building, modify the MODEL_PATH defined in the code.

$ g++ santa.cc -I . -I build/_deps/highway-src -I build/_deps/sentencepiece-src build/libgemma.a build/_deps/highway-build/libhwy.a build/_deps/sentencepiece-build/src/libsentencepiece.so -lstdc++ -l


$ LD_LIBRARY_PATH=./build/_deps/sentencepiece-build/src ./a.out

It will read the text from letter.txt and generate a letter from Santa Claus.

NOTE: the text generation on Raspberry Pi may take some time.

Image of C++ application in libgemma

And here’s the final result later:

Image of C++ app letter from Santa output

C. If you prefer to use llama.cpp, we provide GGUF model as well

$ ./main -m models/gemma-2b-it.gguf --repeat-penalty 1.0 -p You are Santa Claus, write a letter back from this kid.\n<start_of_turn>user\nPLACE_THE_CONTEXT_OF_LETTER_HERE<end_of_turn>\n<start_of_turn>model\n
Image of llama.cpp build and output


Gemma offers limitless possibilities. We hope these suggestions inspire you, and we eagerly anticipate seeing your creations come to life.

We encourage you to join the Google Developer Community Discord server. There, you can share your projects and connect with other like-minded individuals.

Happy tinkering!