Instructions to use Miladasghari/light-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Miladasghari/light-coder with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Miladasghari/light-coder")
model = AutoModelForCausalLM.from_pretrained("Miladasghari/light-coder", 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 Miladasghari/light-coder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Miladasghari/light-coder

SGLang

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

Docker Model Runner
How to use Miladasghari/light-coder with Docker Model Runner:
```
docker model run hf.co/Miladasghari/light-coder
```

light-coder / README.md

Miladasghari

Update README.md

9c1b53f verified 12 days ago

preview code

Raw

History Blame Contribute Delete

2.07 kB

	---
	base_model: Qwen/Qwen2.5-0.5B-Instruct
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- code
	- coding
	- qwen
	- qwen2
	- slm
	- trl
	- fine-tuned
	license: apache-2.0
	language:
	- en
	- code
	---

	# light-coder

	`light-coder` is an ultra-lightweight, standalone instruction-tuned coding model created by fine-tuning [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on ~122k programming instruction-response pairs and merging the LoRA weights directly into the base checkpoint.

	At under 1 GB in size, it requires minimal VRAM, executes quickly on consumer GPUs and CPUs, and integrates out-of-the-box with tools like vLLM, Ollama, and standard Hugging Face pipelines.

	## Model Details

	- Developed by: Milad Asghari
	- Model Name: light-coder
	- Base Model: [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
	- Model Type: Causal Language Model (Full Merged Weights)
	- Primary Domain: Code generation, refactoring, and programming instruction-following
	- Language(s): English, Multiple Programming Languages
	- License: Apache-2.0
	- Size: 988 MB (`safetensors`)

	## How to Get Started

	Because the weights are merged, you do not need the `peft` library for inference:

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "Miladasghari/light-coder"

	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	dtype=torch.float16,
	device_map="auto"
	)

	messages = [
	{"role": "user", "content": "Write a Python function to check if a string is a palindrome."}
	]

	prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

	outputs = model.generate(
	**inputs,
	max_new_tokens=256,
	temperature=0.3,
	top_p=0.9,
	repetition_penalty=1.05
	)

	response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
	print(response)