from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
import torch

model = AutoPeftModelForCausalLM.from_pretrained(
    "path/to/model",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")

prompt = "What is Section 80C in income tax?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Data

The model was fine-tuned on income tax related questions and answers.

Limitations

Specialized for Indian income tax domain
May not perform well on general queries
Tax laws change frequently - verify information independently

Nareshedagotti/income-tax-llama-lora

Income Tax Llama - Fine-tuned Model

Model Details

Usage

Training Data

Limitations

Nareshedagotti/
income-tax-llama-lora