Instructions to use PhysicsWallahAI/Aryabhata-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PhysicsWallahAI/Aryabhata-1.0 with Transformers:

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

pipe = pipeline("text-generation", model="PhysicsWallahAI/Aryabhata-1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PhysicsWallahAI/Aryabhata-1.0")
model = AutoModelForCausalLM.from_pretrained("PhysicsWallahAI/Aryabhata-1.0")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PhysicsWallahAI/Aryabhata-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PhysicsWallahAI/Aryabhata-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PhysicsWallahAI/Aryabhata-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PhysicsWallahAI/Aryabhata-1.0

SGLang

How to use PhysicsWallahAI/Aryabhata-1.0 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 "PhysicsWallahAI/Aryabhata-1.0" \
    --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": "PhysicsWallahAI/Aryabhata-1.0",
		"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 "PhysicsWallahAI/Aryabhata-1.0" \
        --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": "PhysicsWallahAI/Aryabhata-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PhysicsWallahAI/Aryabhata-1.0 with Docker Model Runner:
```
docker model run hf.co/PhysicsWallahAI/Aryabhata-1.0
```

Why not OpenSource the Dataset and Training code?

by SnehitVaddi - opened Jul 22, 2025

Discussion

SnehitVaddi

Jul 22, 2025

As mentioned in the title.

HackNetAyush

Jul 22, 2025

Hi! Just wanted to clarify — I think the dataset might have been open-sourced already. There's this one published by the team that seems very likely to be the one used for training:
🔗 https://huggingface.co/datasets/PhysicsWallahAI/JEE-Main-2025-Math

It’s not explicitly mentioned in the model card, so I can’t say for sure if it’s the exact dataset used — but it seems like a strong possibility given the timing and topic.
Hope that helps!

FA5I

Jul 22, 2025

The original dataset contains 130k data points, that data set is not the training set.

HackNetAyush

Jul 22, 2025

Ah, sorry! It turns out this is just an evaluation dataset — the original dataset hasn’t been released. I also didn’t check it very thoroughly, so apologies for any confusion.

venubanaras

Jul 23, 2025

I don't think they will release the code or the dataset. None of the companies will. However, we can contribute in building use cases for them

deleted

Jul 25, 2025

@HackNetAyush

Hi! Just wanted to clarify — I think the dataset might have been open-sourced already. There's this one published by the team that seems very likely to be the one used for training:
🔗 https://huggingface.co/datasets/PhysicsWallahAI/JEE-Main-2025-Math

It’s not explicitly mentioned in the model card, so I can’t say for sure if it’s the exact dataset used — but it seems like a strong possibility given the timing and topic.
Hope that helps!

This is the evaluation dataset used for benchmarking the result on jee mains .

deleted changed discussion status to closed Jul 26, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment