Instructions to use Lite-Coder/LiteCoder-Terminal-30b-a3b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lite-Coder/LiteCoder-Terminal-30b-a3b-sft with Transformers:

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

pipe = pipeline("text-generation", model="Lite-Coder/LiteCoder-Terminal-30b-a3b-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lite-Coder/LiteCoder-Terminal-30b-a3b-sft")
model = AutoModelForCausalLM.from_pretrained("Lite-Coder/LiteCoder-Terminal-30b-a3b-sft")
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 Lite-Coder/LiteCoder-Terminal-30b-a3b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lite-Coder/LiteCoder-Terminal-30b-a3b-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lite-Coder/LiteCoder-Terminal-30b-a3b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lite-Coder/LiteCoder-Terminal-30b-a3b-sft

SGLang

How to use Lite-Coder/LiteCoder-Terminal-30b-a3b-sft 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 "Lite-Coder/LiteCoder-Terminal-30b-a3b-sft" \
    --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": "Lite-Coder/LiteCoder-Terminal-30b-a3b-sft",
		"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 "Lite-Coder/LiteCoder-Terminal-30b-a3b-sft" \
        --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": "Lite-Coder/LiteCoder-Terminal-30b-a3b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lite-Coder/LiteCoder-Terminal-30b-a3b-sft with Docker Model Runner:
```
docker model run hf.co/Lite-Coder/LiteCoder-Terminal-30b-a3b-sft
```

Lite-Coder commited on 7 days ago

Commit

9aa54ae

verified ·

1 Parent(s): ef4daed

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -8,10 +8,9 @@ pipeline_tag: text-generation
 ## **LiteCoder-Terminal-30b-a3b-sft**
-**LiteCoder-Terminal-30b-a3b-sft** is part of our latest release on lightweight code agents. The model is fine-tuned from `Qwen3-30B-A3B-Instruct-2507` on the [LiteCoder-Terminal-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT) dataset.
-- **Paper:** [LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents](https://huggingface.co/papers/2605.29559)
-- **Code:** [https://github.com/icip-cas/LiteCoder](https://github.com/icip-cas/LiteCoder)
 Compared to our previous preview version, we scaled up the training data from under 1,000 samples to 11,255 trajectories, incorporating a broader task taxonomy and diverse agent scaffolds. With these updates, the model shows consistent improvements across Terminal Bench evaluations.

 ## **LiteCoder-Terminal-30b-a3b-sft**
+[**Paper**](https://huggingface.co/papers/2605.29559) | [**Code**](https://github.com/icip-cas/LiteCoder) | [**Blog Post**](https://huggingface.co/blog/Lite-Coder/releasing-litecoder-terminal)
+**LiteCoder-Terminal-30b-a3b-sft** is part of our latest release on lightweight code agents. The model is fine-tuned from `Qwen3-30B-A3B-Instruct-2507` on the [LiteCoder-Terminal-SFT](https://huggingface.co/datasets/Lite-Coder/LiteCoder-Terminal-SFT) dataset.
 Compared to our previous preview version, we scaled up the training data from under 1,000 samples to 11,255 trajectories, incorporating a broader task taxonomy and diverse agent scaffolds. With these updates, the model shows consistent improvements across Terminal Bench evaluations.