The Indic-gemma-7b-finetuned-sft-Navarasa-2.0 model by Telugu-LLM-Labs is an 8.5 billion parameter instruction-tuned language model based on Google's Gemma-7b architecture. It has been LoRA fine-tuned on 15 Indian languages and English, making it specialized for multilingual instruction-following tasks across these languages. With a context length of 8192 tokens, this model is optimized for generating responses in a diverse set of Indic languages.
No reviews yet. Be the first to review!
Hugging Face