Instructions to use Sushilmishrawork/india-state-debt-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sushilmishrawork/india-state-debt-llm with Transformers:

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

pipe = pipeline("text-generation", model="Sushilmishrawork/india-state-debt-llm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sushilmishrawork/india-state-debt-llm")
model = AutoModelForCausalLM.from_pretrained("Sushilmishrawork/india-state-debt-llm", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sushilmishrawork/india-state-debt-llm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sushilmishrawork/india-state-debt-llm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sushilmishrawork/india-state-debt-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sushilmishrawork/india-state-debt-llm

SGLang

How to use Sushilmishrawork/india-state-debt-llm 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 "Sushilmishrawork/india-state-debt-llm" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sushilmishrawork/india-state-debt-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Sushilmishrawork/india-state-debt-llm" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sushilmishrawork/india-state-debt-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sushilmishrawork/india-state-debt-llm with Docker Model Runner:
```
docker model run hf.co/Sushilmishrawork/india-state-debt-llm
```

🇮🇳 India State Debt LLM (Chain-of-Thought Fiscal Reasoning Model)

A domain-specific Large Language Model fine-tuned on official Reserve Bank of India (RBI) and State Budget financial data for analyzing public liabilities, Debt-to-GSDP percentages, per-capita debt, national rankings, and multi-year growth trajectories (2020–2026) across 31 Indian States and Union Territories.

Usage with Hugging Face `transformers`

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

model_id = "your-hf-username/india-state-debt-llm"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

prompt = "Instruction: Display Karnataka debt growth from 2020-2026\nResponse:\n<thought>\n"
response = generator(prompt, max_new_tokens=300, temperature=0.7)

print(response[0]["generated_text"])

Response Output Structure

The model generates responses structured into 3 explicit Chain-of-Thought stages:

<thought>: Step-by-step query parsing, record identification, and fiscal metrics retrieval.
<analysis>: Structured financial metrics, rank, per-capita figures, and category indicators.
<answer>: Executive summary answer.

Downloads last month: -

Safetensors

Model size

0.1B params

Tensor type

F32

Sushilmishrawork
/

india-state-debt-llm

🇮🇳 India State Debt LLM (Chain-of-Thought Fiscal Reasoning Model)

Usage with Hugging Face `transformers`

Response Output Structure

Space using Sushilmishrawork/india-state-debt-llm 1

🇮🇳 India State Debt LLM (Chain-of-Thought Fiscal Reasoning Model)

Usage with Hugging Face transformers

Response Output Structure

Space using Sushilmishrawork/india-state-debt-llm 1

Usage with Hugging Face `transformers`