Instructions to use Cialtion/SimpleTool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cialtion/SimpleTool with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Cialtion/SimpleTool")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Cialtion/SimpleTool", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Cialtion/SimpleTool with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Cialtion/SimpleTool" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cialtion/SimpleTool", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Cialtion/SimpleTool
- SGLang
How to use Cialtion/SimpleTool 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 "Cialtion/SimpleTool" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cialtion/SimpleTool", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "Cialtion/SimpleTool" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cialtion/SimpleTool", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Cialtion/SimpleTool with Docker Model Runner:
docker model run hf.co/Cialtion/SimpleTool
Update prompts/scenarios.json
Browse files- prompts/scenarios.json +29 -0
prompts/scenarios.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"name": "Game — Tower Defense",
|
| 4 |
+
"tools_file": "tools_game.jsonl",
|
| 5 |
+
"system": "You are the voice command interpreter for a real-time tower defense game. The player issues orders by voice. You convert ASR-transcribed commands into function calls.\n\nRules:\n- One function call per command\n- Fuzzy match operator names\n- Positions: north, south, east, west, center\n- If all tasks in history are done, call pass",
|
| 6 |
+
"query": "Wave 5, BOSS appeared, 8 enemies remaining\nOperators: Blaze(north,HP50%,skill ready) Amiya(center,HP90%,skill ready)\nEnemy direction: concentrated north\n\nAmiya use skill now",
|
| 7 |
+
"history": "[]",
|
| 8 |
+
"expected": "use_skill",
|
| 9 |
+
"desc": "use_skill(Amiya)"
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"name": "Robotic Arm — Assembly",
|
| 13 |
+
"tools_file": "tools_arm.jsonl",
|
| 14 |
+
"system": "You are the voice controller for an industrial 6-axis robotic arm. You convert spoken commands into function calls.\n\nRules:\n- One function call per command\n- Coordinates in mm, angles in degrees\n- Gripper force: light=10N, medium=50N, heavy=100N\n- Speed: slow/normal/fast",
|
| 15 |
+
"query": "Arm at home (0,0,500), gripper open\nWorkpiece: red gear at (300,150,50), target tray at (600,0,80)\n\nMove to the red gear position slowly",
|
| 16 |
+
"history": "[]",
|
| 17 |
+
"expected": "move_to",
|
| 18 |
+
"desc": "move_to(300,150,50,slow)"
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"name": "Digital Human — Streamer",
|
| 22 |
+
"tools_file": "tools_avatar.jsonl",
|
| 23 |
+
"system": "You are the expression controller for a virtual digital human streamer. You convert director instructions into animation function calls.\n\nRules:\n- One function call per instruction\n- Emotion intensity: 0.0-1.0\n- Speech text should be natural\n- Tone: cheerful/calm/serious/excited",
|
| 24 |
+
"query": "Stream just started, viewers flooding in\nChat: \"Hello streamer!\" \"Good evening!\"\nDirector: greet the audience warmly, say welcome and look at camera",
|
| 25 |
+
"history": "[]",
|
| 26 |
+
"expected": "speak",
|
| 27 |
+
"desc": "speak(welcome,cheerful)"
|
| 28 |
+
}
|
| 29 |
+
]
|