llama2_med_finetuned

Model Card for Model ID

This repo contains the LoRA adapter weights for a fine-tuned Llama-2 7B Chat model designed for medical question answering and healthcare-related conversations.

Model Details

Model Description

Developed by: Lalitaditya M

Model type: LoRA Adapter

Finetuned from model: NousResearch/Llama-2-7b-chat-hf

---

How to Get Started with the Model

Use the code below to load the base model and apply the LoRA adapter.

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model = "NousResearch/Llama-2-7b-chat-hf"
adapter = "Lalitadityaa/llama2_med_finetuned"

tokenizer = AutoTokenizer.from_pretrained(base_model)

model = AutoModelForCausalLM.from_pretrained(
    base_model,
    torch_dtype="auto",
    device_map="auto",
    load_in_4bit=True,
)

model = PeftModel.from_pretrained(model, adapter)

Framework Versions

• PEFT 0.13.2