abhinand/gemma-2b-tamil
TEXT GENERATIONConcurrency Cost:1Model Size:2.6BQuant:BF16Ctx Length:8kPublished:Feb 25, 2024License:gemma-terms-of-useArchitecture:Transformer0.0K Warm

The abhinand/gemma-2b-tamil is a 2.6 billion parameter foundational language model, continually pretrained from Google Gemma 2B, specifically adapted for the Tamil language. Developed by Abhinand Balachandran, this experimental model focuses on causal language modeling in both English and Tamil, without expanding the original Gemma vocabulary. It demonstrates promising bilingual capabilities for a 2B parameter model, particularly for Tamil language generation and understanding.

Loading preview...