Fine-tuned Mistral-7B-Instruct-v0.3 with LoRA on Salesforce Function Dataset (~60K samples) for AI finance Agent, deployed full scale LLM model (14.5GB) via Hugging Face python transformers library and LoRA (PEFT, 715MB) for scalability.
Please let me know any improvements it requires, your ideas and feedback are always welcomed as I am still new to this and still learning.