Piccolo-9B is a decision model for tool review and context selection. This repository contains the complete Safetensors checkpoint.
hf download agentscope-ai/Piccolo-9B --local-dir Piccolo-9B
Use the included reference implementation for bidirectional attention and candidate scoring.
python -m pip install -r Piccolo-9B/requirements.txt
python Piccolo-9B/piccolo_inference.py --model Piccolo-9B --request request.json --device cuda:0
Use the request example to prepare request.json.
Use Piccolo locally for tool review and context selection with the QwenPaw setup guide.
| HarnessJevBench Hard ↑ | DataJevBench ↑ | JevBench Public ↑ | Decision Index Public ↑ |
|---|---|---|---|
| 68.81% | 69.40% | 89.61% | 60.86 |
Benchmark results are for the full checkpoint.
This model is also available on ModelScope.
model-00001-of-00004.safetensors 5.3 GBmodel-00002-of-00004.safetensors 5.3 GBmodel-00003-of-00004.safetensors 5.2 GBmodel-00004-of-00004.safetensors 2.0 GBmodel-frozen-auxiliary.safetensors 1.4 GB