Instructions to use SamuelBang/AesCoder-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SamuelBang/AesCoder-4B with Transformers:

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

pipe = pipeline("text-generation", model="SamuelBang/AesCoder-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SamuelBang/AesCoder-4B")
model = AutoModelForCausalLM.from_pretrained("SamuelBang/AesCoder-4B")
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

vLLM

How to use SamuelBang/AesCoder-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SamuelBang/AesCoder-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": "SamuelBang/AesCoder-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SamuelBang/AesCoder-4B

SGLang

How to use SamuelBang/AesCoder-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 "SamuelBang/AesCoder-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": "SamuelBang/AesCoder-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 "SamuelBang/AesCoder-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": "SamuelBang/AesCoder-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SamuelBang/AesCoder-4B with Docker Model Runner:
```
docker model run hf.co/SamuelBang/AesCoder-4B
```

Improve model card: Add metadata, news, abstract, to-do list, and GitHub link

by nielsr HF Staff - opened Oct 29, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+18

-3

nielsr

Oct 29, 2025

This PR significantly enhances the model card for AesCoder-4B by:

Adding the pipeline_tag: text-generation for accurate categorization and improved discoverability on the Hugging Face Hub.
Specifying library_name: transformers to enable the automated "how to use" widget, as the model is explicitly compatible with the transformers library.
Including the license: apache-2.0 for clear licensing information, based on common practice for similar models.
Adding the Hugging Face model badge from the project's GitHub README to the introductory section.
Incorporating an explicit link to the GitHub repository for easy access to the codebase.
Integrating the `

Improve model card: Add metadata, news, abstract, to-do list, and GitHub linkc246703f

SamuelBang changed pull request status to merged Oct 29, 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