Open Insurance L L M Llama3 8 B

Introduction

The Open-Insurance-LLM-Llama3-8B is a domain-specific language model based on Nvidia Llama 3 ChatQA. It is fine-tuned for insurance-related queries, leveraging the Llama 3 architecture to handle tasks within the insurance domain effectively.

Architecture

• Model Type: Instruction-tuned Language Model
• Base Model: nvidia/Llama3-ChatQA-1.5-8B
• Finetuned Model: Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B
• Quantized Model: Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B-GGUF
• Model Architecture: Llama
• Parameters: 8.05 billion
• Language: English

The model features enhanced attention mechanisms from Llama 3 and the ChatQA 1.5 instruction-tuning framework, with adaptations specific to the insurance domain.

Training

The model has been fine-tuned on the InsuranceQA dataset using LoRA (8 bit), focusing on insurance-specific question-answer pairs and domain knowledge. It features 20.97 million trainable parameters, representing 0.26% of the total 8.05 billion parameters.

Guide: Running Locally

1. Clone the Repository:

   • Download the model files from Hugging Face Model Hub.

2. Install Dependencies:

   • Ensure that you have Python and PyTorch installed. Install the transformers library using pip install transformers.

3. Load the Model:

   from transformers import AutoModelForCausalLM, AutoTokenizer
   
   tokenizer = AutoTokenizer.from_pretrained("Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B")
   model = AutoModelForCausalLM.from_pretrained("Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B")
   

4. Run Inference:

   • Use the model for text generation tasks related to insurance queries.

5. Cloud GPUs:

   • For better performance, consider using cloud-based GPUs such as AWS EC2, Google Cloud, or Azure.

License

The model is licensed under the llama3 license. Users should ensure compliance with the terms outlined by this license when using the model.