Instructions to use Fadilahnuryasin/Assistant-Coding-Python with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fadilahnuryasin/Assistant-Coding-Python with Transformers:

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

pipe = pipeline("text-generation", model="Fadilahnuryasin/Assistant-Coding-Python")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fadilahnuryasin/Assistant-Coding-Python")
model = AutoModelForCausalLM.from_pretrained("Fadilahnuryasin/Assistant-Coding-Python", 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 Fadilahnuryasin/Assistant-Coding-Python with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Fadilahnuryasin/Assistant-Coding-Python

SGLang

How to use Fadilahnuryasin/Assistant-Coding-Python 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 "Fadilahnuryasin/Assistant-Coding-Python" \
    --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": "Fadilahnuryasin/Assistant-Coding-Python",
		"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 "Fadilahnuryasin/Assistant-Coding-Python" \
        --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": "Fadilahnuryasin/Assistant-Coding-Python",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fadilahnuryasin/Assistant-Coding-Python with Docker Model Runner:
```
docker model run hf.co/Fadilahnuryasin/Assistant-Coding-Python
```

Model Card for Assistant-Coding-Python

Model Details

Model Description

Assistant-Coding-Python is a fine-tuned causal language model based on SmolLM2-360M. It is specifically trained to assist and answer various Python programming questions, ranging from implementing basic mathematical functions to data structure manipulation.

Developed by: Fadilahnuryasin
Model type: Causal Language Model (Fine-tuned with Supervised Fine-Tuning)
Language(s) (NLP): English, Python
License: MIT
Finetuned from model: HuggingFaceTB/SmolLM2-360M

Uses

Direct Use

This model is designed to act as a coding assistant, helping users write Python code, solve basic logic problems, and understand Python syntax.

Out-of-Scope Use

This model is not designed for deployment in critical systems requiring high safety verification or complex, enterprise-scale code generation without human supervision.

Bias, Risks, and Limitations

As a small-scale model (360M parameters), it may occasionally produce inaccurate outputs on complex mathematical logic or incorrectly predict final execution results. Users are advised to review and test all generated code before use.

How to Get Started with the Model

Use the code below to get started with the model using the Transformers library:

from transformers import pipeline

pipe = pipeline("text-generation", model="Fadilahnuryasin/Assistant-Coding-Python")
messages = [
    {"role": "system", "content": "You are an expert and helpful Python programming assistant."},
    {"role": "user", "content": "Create a Python function to calculate the area of a rectangle."}
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=200, do_sample=True, temperature=0.2)
print(outputs[0]["generated_text"])

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

F32

F16