Instructions to use lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP with Transformers:

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

pipe = pipeline("text-generation", model="lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP")
model = AutoModelForCausalLM.from_pretrained("lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP

SGLang

How to use lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP 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 "lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP" \
    --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": "lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP",
		"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 "lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP" \
        --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": "lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP with Docker Model Runner:
```
docker model run hf.co/lightonai/SASS-MiniCPM5-1B-Weighted-SFT-GREP
```

SASS-MiniCPM5-1B-Weighted-SFT-GREP

Full model checkpoint for repository code localization using the grep harness.

Weighted supervised fine-tuning of openbmb/MiniCPM5-1B on 13,550 clean multilingual DeepSeek-V4-Flash-0731 trajectories, using configuration grep, split sft. Injected teacher finish reminders were removed from student training data.

Use the system prompt and tool schemas in student-protocol.json with the included tokenizer and chat template. The model requires an external harness to execute tool calls; repository snapshots and search indexes are not included. ColGREP models use semantic search; GREP models use lexical search through the terminal.

The original training configuration is included for provenance; local paths in that file must be adapted for another environment. provenance.json records checkpoint identity and SHA-256 hashes. Model weights are unchanged from the evaluated local checkpoint. Upstream base-model terms apply.

Consolidated data and reproducibility

Load lightonai/SASS-Data with configuration grep and split sft for weighted demonstrations or rl for RL tasks. The SFT tools column is JSON text; decode it before applying the chat template. Weights and tokenizer files are unchanged by the repository rename.