konkani-Llama
Collection
Fintuned LLama model for konkani • 1 item • Updated
Konkani-Llama-3.1-8B-Instruct
This model is a parameter-efficient fine-tune (LoRA) of Meta-Llama-3.1-8B-Instruct, specifically optimized for the Konkani language across its three official scripts: Devanagari, Romi (Latin), and Kannada. It was fine-tuned on the Konkani-Instruct-100k dataset.
💻 How to Use (Inference)
First, make sure you have the required libraries installed:
pip install transformers torch accelerate peft
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for konkani/konkani-llama3.1-8b-instruct
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct