Instructions to use Tesleum/shirdel-agent-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
NeMo
How to use Tesleum/shirdel-agent-4b with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```

How to use Tesleum/shirdel-agent-4b with Transformers:

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

pipe = pipeline("text-generation", model="Tesleum/shirdel-agent-4b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tesleum/shirdel-agent-4b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Tesleum/shirdel-agent-4b", trust_remote_code=True, 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tesleum/shirdel-agent-4b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tesleum/shirdel-agent-4b

SGLang

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

Unsloth Desktop
Docker Model Runner
How to use Tesleum/shirdel-agent-4b with Docker Model Runner:
```
docker model run hf.co/Tesleum/shirdel-agent-4b
```

Shirdel-Agent-4B

Agent/Programming models were designed to solve mathematical problems by integrating text-based reasoning with code blocks executed by Python interpreter. The models were trained on python-edu-cleaned, a math instruction tuning dataset with 7.6M problem-solutions:

Best performance on tasks that resemble the training data
Better Python explanations
Calibrated idiomatic Python code
Better handling of educational programming prompts
Improved debugging advice
More consistent code formatting

We did not reduce the quality of the model and for some reason did not use quantization for code quality.

	greedy		majority@50
model	GSM8K	MATH	GMS8K	MATH
Shirdel-Agent-4B	65.9	53.6	94.8	65.6
Shirdel-Agent-4B	90.2	54.5	96.9	67.2
Shirdel-Agent-4B	88.8	55.5	96.8	67.6
Shirdel-Agent-4B	90.7	58.3	98.0	70.2
Shirdel-Agent-4B	94.7	56.3	99.1	68.3
Shirdel-Agent-4B	94.6	60.7	99.8	70.4