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
```

Add library name, pipeline tag and links to paper/code

by nielsr HF Staff - opened 9 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-4

Files changed (1) hide show

README.md +9 -4

README.md CHANGED Viewed

@@ -1,14 +1,19 @@
 ---
-license: mit
 base_model:
-  - Qwen/Qwen3-30B-A3B-Instruct-2507
 ---
 ## **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.
-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.
 ## **Released Artifacts**

 ---
 base_model:
+- Qwen/Qwen3-30B-A3B-Instruct-2507
+license: mit
+library_name: transformers
+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.
 ## **Released Artifacts**