kundan621/tinyllama-makemytrip-financial-qa

TinyLlama MakeMyTrip Financial QA

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 specifically for answering financial questions about MakeMyTrip.

Model Details

• Base Model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
• Fine-tuning Method: LoRA (Low-Rank Adaptation) with PEFT
• Domain: Financial Question Answering
• Company: MakeMyTrip
• Language: English

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("kundan621/tinyllama-makemytrip-financial-qa")
tokenizer = AutoTokenizer.from_pretrained("kundan621/tinyllama-makemytrip-financial-qa")

# Format your prompt
prompt = "<|system|>\nYou are a helpful assistant that provides financial data from MakeMyTrip reports.</s>\n<|user|>\nWhat was the total revenue in 2024?</s>\n<|assistant|>\n"

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Data

The model was fine-tuned on MakeMyTrip financial statements and reports covering:

• Revenue data (2023-2025)
• Financial metrics
• Balance sheet information
• Cash flow statements

Limitations

This model is specifically trained for MakeMyTrip financial data and may not perform well on general financial questions or other companies' data.