Instructions to use Edaizi/KG-TRACES with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Edaizi/KG-TRACES with Transformers:

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

pipe = pipeline("text-generation", model="Edaizi/KG-TRACES")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Edaizi/KG-TRACES")
model = AutoModelForCausalLM.from_pretrained("Edaizi/KG-TRACES")
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 Edaizi/KG-TRACES with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Edaizi/KG-TRACES

SGLang

How to use Edaizi/KG-TRACES 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 "Edaizi/KG-TRACES" \
    --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": "Edaizi/KG-TRACES",
		"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 "Edaizi/KG-TRACES" \
        --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": "Edaizi/KG-TRACES",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Edaizi/KG-TRACES with Docker Model Runner:
```
docker model run hf.co/Edaizi/KG-TRACES
```

Enhance model card with metadata, paper link, usage example, and dataset info

by nielsr HF Staff - opened Oct 25, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+88

-3

nielsr

Oct 25, 2025

This PR significantly improves the model card for KG-TRACES by adding crucial metadata and essential documentation.

Key changes include:

Metadata: Added pipeline_tag: text-generation to classify the model's primary function and library_name: transformers to indicate its compatibility with the Hugging Face Transformers library. Also added the relevant datasets (Edaizi/KG-TRACES-WebQSP, Edaizi/KG-TRACES-CWQ) for discoverability.
Paper Link: Linked the model to its official paper: KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision.
Code Repository: Added a direct link to the GitHub repository for easy access to the code: https://github.com/Edaizi/KG-TRACES.
Sample Usage: Included a Python code snippet to demonstrate how to load and use the model, directly sourced from the GitHub README.
Descriptive Content: Incorporated an overview, key highlights, and dataset information from the paper abstract and GitHub README.
Visuals: Embedded key images from the GitHub repository to enhance understanding.
Citation: Added the BibTeX citation for proper attribution.

These additions will make the model more discoverable and user-friendly on the Hugging Face Hub.

Enhance model card with metadata, paper link, usage example, and dataset infoc1cf5a6b

Edaizi changed pull request status to merged Oct 25, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment