Instructions to use nalandabh/bihar-360m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nalandabh/bihar-360m with Transformers:

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

pipe = pipeline("text-generation", model="nalandabh/bihar-360m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nalandabh/bihar-360m")
model = AutoModelForCausalLM.from_pretrained("nalandabh/bihar-360m", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nalandabh/bihar-360m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nalandabh/bihar-360m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nalandabh/bihar-360m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nalandabh/bihar-360m

SGLang

How to use nalandabh/bihar-360m 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 "nalandabh/bihar-360m" \
    --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": "nalandabh/bihar-360m",
		"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 "nalandabh/bihar-360m" \
        --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": "nalandabh/bihar-360m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nalandabh/bihar-360m with Docker Model Runner:
```
docker model run hf.co/nalandabh/bihar-360m
```

bihar-360m

A small (360M) English model that answers questions about Bihar, India, from a passage you give it. If the passage doesn't contain the answer, it says so.

It is a reader, not an encyclopedia: without a passage it will guess. Check important answers.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "nalandabh/bihar-360m"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo)

SYSTEM = ("You are a helpful assistant for questions about Bihar. Answer only from the provided context. "
          "If the context does not contain the answer, say you don't have that information.")
passage = "Paste a passage about Bihar here."
question = "Your question here?"

messages = [
    {"role": "system", "content": SYSTEM},
    {"role": "user", "content": f"Context:\n{passage}\n\nQuestion: {question}"},
]
ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
out = model.generate(ids, max_new_tokens=150, do_sample=False)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

Use this exact prompt format. When the passage lacks the answer, the reply is: "I don't have that information in the provided text."

Training

Fine-tuned from SmolLM2-360M-Instruct with LoRA. Question-answer pairs were generated from Bihar text chunks with Qwen3-8B and filtered for accuracy. English only.

Text sources: English Wikipedia (CC BY-SA 4.0), Wikidata (CC0) and pages from Grokipedia (grokipedia.com). See ATTRIBUTION.md for the page list.

Limits

v0.1, an early version. English only. Not for legal, medical or official decisions.

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for nalandabh/bihar-360m

Base model

HuggingFaceTB/SmolLM2-360M

Quantized

HuggingFaceTB/SmolLM2-360M-Instruct

Finetuned

(194)

this model