metadata
language:
- ko
Model Overview Model Name: Llama3 8B Instruct (Fine-Tuned with LoRA)
Model Type: Language Model
Base Model: Llama3 8B Instruct
Fine-Tuning Technique: Low-Rank Adaptation (LoRA)
Description This model is based on the Llama3 8B Instruct, a state-of-the-art language model, and has been fine-tuned using the LoRA. LoRA allows for efficient fine-tuning with fewer parameters, making the model more adaptable and faster to deploy for specific tasks.
Train GPU: A100
Training Time: 25 hours