Finance LLaMA-2-7B Chat LoRA (QLoRA, 4-bit quantized) – a LoRA fine-tuned version of meta-llama/Llama-2-7b-chat-hf, trained on a finance-specific dataset. This model also integrates the Yahoo Finance API to fetch live stock market data for real-time responses.

Developed by: Aayush Pandey
Model type: Causal Language Model (LLM)
Language(s) (NLP): English
License: MIT
Finetuned from model: meta-llama/Llama-2-7b-chat-hf
Libraries used: PEFT, Transformers, BitsAndBytes, Gradio

Uses

Direct Use

Answer finance-related questions
Provide real-time stock data insights using Yahoo Finance
Serve as an AI assistant for stock market queries

Downstream Use

Can be integrated into web apps, dashboards, or chatbots
Can be fine-tuned further for domain-specific financial analysis

Out-of-Scope Use

Non-finance related tasks may produce nonsensical outputs
Real-time trading advice should not be treated as financial advice

Bias, Risks, and Limitations

Model may reflect biases present in training data
Model outputs may be inaccurate or outdated for financial decisions
Not suitable for critical or high-stakes trading decisions

Recommendations

Users should verify any financial information generated and be aware that the model is not a substitute for professional advice.

How to Get Started with the Model

python

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

adapter_repo = "aaysush16/finance-llama-2-7b-lora"
base_model = "meta-llama/Llama-2-7b-chat-hf"

tokenizer = AutoTokenizer.from_pretrained(adapter_repo)
model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto")
model = PeftModel.from_pretrained(model, adapter_repo)
model.eval()

prompt = "Tell me about AAPL stock"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))