Instructions to use kundan621/tinyllama-makemytrip-financial-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kundan621/tinyllama-makemytrip-financial-qa with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kundan621/tinyllama-makemytrip-financial-qa")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kundan621/tinyllama-makemytrip-financial-qa")
model = AutoModelForCausalLM.from_pretrained("kundan621/tinyllama-makemytrip-financial-qa")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use kundan621/tinyllama-makemytrip-financial-qa with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kundan621/tinyllama-makemytrip-financial-qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kundan621/tinyllama-makemytrip-financial-qa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kundan621/tinyllama-makemytrip-financial-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kundan621/tinyllama-makemytrip-financial-qa

SGLang

How to use kundan621/tinyllama-makemytrip-financial-qa with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kundan621/tinyllama-makemytrip-financial-qa" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kundan621/tinyllama-makemytrip-financial-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kundan621/tinyllama-makemytrip-financial-qa" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kundan621/tinyllama-makemytrip-financial-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kundan621/tinyllama-makemytrip-financial-qa with Docker Model Runner:
```
docker model run hf.co/kundan621/tinyllama-makemytrip-financial-qa
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

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.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

F32

Model tree for kundan621/tinyllama-makemytrip-financial-qa

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Adapter

(1547)

this model

kundan621
/

tinyllama-makemytrip-financial-qa