Instructions to use AdithyaSK/data-agent-4b-normal-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdithyaSK/data-agent-4b-normal-final with Transformers:

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

pipe = pipeline("text-generation", model="AdithyaSK/data-agent-4b-normal-final")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("AdithyaSK/data-agent-4b-normal-final")
model = AutoModelForMultimodalLM.from_pretrained("AdithyaSK/data-agent-4b-normal-final", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AdithyaSK/data-agent-4b-normal-final with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdithyaSK/data-agent-4b-normal-final"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdithyaSK/data-agent-4b-normal-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AdithyaSK/data-agent-4b-normal-final

SGLang

How to use AdithyaSK/data-agent-4b-normal-final 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 "AdithyaSK/data-agent-4b-normal-final" \
    --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": "AdithyaSK/data-agent-4b-normal-final",
		"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 "AdithyaSK/data-agent-4b-normal-final" \
        --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": "AdithyaSK/data-agent-4b-normal-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AdithyaSK/data-agent-4b-normal-final with Docker Model Runner:
```
docker model run hf.co/AdithyaSK/data-agent-4b-normal-final
```

data-agent-4b-normal-final (v0)

A 4B data-science agent finetuned from Qwen/Qwen3.5-4B with GRPO (online RL) to solve data-analysis tasks in a sandboxed bash environment. This repo holds the final checkpoint (end of a full 1-epoch run) of the 4b-normal run.

Training

Method: GRPO (Group Relative Policy Optimization) via TRL.
Environment: Harbor task spec + E2B cloud sandboxes; single bash tool, answer submitted to /workdir/answer.txt.
Dataset: AdithyaSK/data_agent_rl_environment_train.
Schedule: 1 epoch (1119 steps), 8 generations/prompt, KL-anchored to the reference. Tasks were presented in random order (standard).
This checkpoint: step 1119 (final).

Evaluation

Agentic pass@k on the held-out data_agent_rl_environment_eval suite (366 tasks, 4 samples/task, unbiased estimator):

metric	base (Qwen3.5-4B)	this model	Δ
pass@1	0.600	0.643	+0.043
pass@2	0.677	0.720	+0.043
pass@3	0.715	0.762	+0.047
pass@4	0.740	0.791	+0.051

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("AdithyaSK/data-agent-4b-normal-final", revision="v0", torch_dtype="bfloat16")
tok = AutoTokenizer.from_pretrained("AdithyaSK/data-agent-4b-normal-final", revision="v0")

Part of the data-agent v0 release. Served non-thinking with a single bash tool (Qwen tool-calling).