Instructions to use faresfawzi/ToolACE-2-8B-SCRIBE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use faresfawzi/ToolACE-2-8B-SCRIBE with Transformers:

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

pipe = pipeline("text-generation", model="faresfawzi/ToolACE-2-8B-SCRIBE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("faresfawzi/ToolACE-2-8B-SCRIBE")
model = AutoModelForCausalLM.from_pretrained("faresfawzi/ToolACE-2-8B-SCRIBE")
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

vLLM

How to use faresfawzi/ToolACE-2-8B-SCRIBE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "faresfawzi/ToolACE-2-8B-SCRIBE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "faresfawzi/ToolACE-2-8B-SCRIBE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/faresfawzi/ToolACE-2-8B-SCRIBE

SGLang

How to use faresfawzi/ToolACE-2-8B-SCRIBE 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 "faresfawzi/ToolACE-2-8B-SCRIBE" \
    --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": "faresfawzi/ToolACE-2-8B-SCRIBE",
		"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 "faresfawzi/ToolACE-2-8B-SCRIBE" \
        --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": "faresfawzi/ToolACE-2-8B-SCRIBE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use faresfawzi/ToolACE-2-8B-SCRIBE with Docker Model Runner:
```
docker model run hf.co/faresfawzi/ToolACE-2-8B-SCRIBE
```

faresfawzi commited on Oct 28, 2025

Commit

2f93bbf

verified ·

1 Parent(s): f63b18d

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -6

README.md CHANGED Viewed

@@ -71,12 +71,6 @@ The model is designed to:
 If you use this model, please cite:
-**APA**
-Fawzi, F., Swamy, V., Glandorf, D., Nazaretsky, T., & Käser, T. (2025).
-*SCRIBE: Structured Chain Reasoning for Interactive Behavior Explanations using Tool Calling*. EPFL.
-Liu, W., Huang, X., Zeng, X., Hao, X., Yu, S., Li, D., Wang, S., Gan, W., Liu, Z., Yu, Y., Wang, Z., Wang, Y., Ning, W., Hou, Y., Wang, B., Wu, C., Xinzhi, W., Liu, Y., Wang, Y., Tang, D., Tu, D., Shang, L., Jiang, X., Tang, R., Lian, D., Liu, Q., & Chen, E. (2025). *ToolACE: Winning the Points of LLM Function Calling*. In ICLR 2025.
 **BibTeX**
 ```bibtex
 @inproceedings{2025-EMNLP-Scribe,

 If you use this model, please cite:
 **BibTeX**
 ```bibtex
 @inproceedings{2025-EMNLP-Scribe,