L

Llama Krikri 8B Base

Developed by ilsp
Llama-Krikri-8B-Base is a large Greek foundational language model built upon Llama-3.1-8B, extending Greek language capabilities through continued pretraining while maintaining English proficiency.
Downloads 104
Release Time : 2/7/2025

Model Overview

This model is a new member of the ILSP open-source Greek large model family, focusing on enhancing Greek language processing while supporting English. Suitable for tasks like text generation.

Model Features

Enhanced Greek language capability
Significantly improved Greek language processing through continued pretraining with 56.7 billion Greek tokens.
Bilingual support
Maintains and slightly improves English capability while enhancing Greek, avoiding catastrophic forgetting.
Extended tokenizer
Extended the Llama-3.1 tokenizer to better support Greek vocabulary.
Long context support
Supports 128k context length, approximately 80,000 Greek words.

Model Capabilities

Greek text generation
English text generation
Bilingual text processing

Use Cases

Language processing
Greek content generation
Generate high-quality Greek text content
Average improvement of 10.8% in Greek benchmark tests
Bilingual application development
Develop applications supporting both Greek and English
Average improvement of 0.8% in English benchmark tests
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase