Skip to content

A finetune of Gemma2B for the purpose of adapting to Czech language and it's cultural context wrapped in the language itself. Originally made for Google's Kaggle competition.

Notifications You must be signed in to change notification settings

quant-eagle/gemma-global-competition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Gemma Czech Adaptation

This repository focuses on adapting Gemma, a pre-trained language model, for the Czech language. We will compile our own datasets from Hugging Face's datasets containing Czech data to fine-tune the model effectively.

This repository serves as our submission for the Gemma Language Model Tuning Competition, where we aim to optimize Gemma's performance on Czech language tasks.

Take this repository's implementation as a proof of concept, for better results we'd need more structured data, optimize the hyperparams and scale the training which will require significantly more resources.

There's a still a possibility for more efficient fine tune (training) using RL techniques such PPO, TRPO, GRPO or alignment techniques such as DPO and maybe some transfer learning.

Objectives

  • Fine-tune Gemma to improve its understanding of the Czech language.
  • Evaluate the model's performance on tasks like translation, sentiment analysis, and natural language generation in Czech.
  • Deploy the fine-tuned model for practical applications.

Repository Structure

  • data/: Directory for datasets used in training and evaluation.
  • models/: Directory to save trained models and checkpoints.

Usage

You can either run the poc (proof of concept) notebook or the final submission one. Then monitor training progress and evaluate results on Czech-specific tasks.

About

A finetune of Gemma2B for the purpose of adapting to Czech language and it's cultural context wrapped in the language itself. Originally made for Google's Kaggle competition.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •