Instructions to use anonymous192837192873/GraphGen-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anonymous192837192873/GraphGen-14b with Transformers:

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

pipe = pipeline("text-generation", model="anonymous192837192873/GraphGen-14b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anonymous192837192873/GraphGen-14b")
model = AutoModelForCausalLM.from_pretrained("anonymous192837192873/GraphGen-14b")
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 anonymous192837192873/GraphGen-14b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anonymous192837192873/GraphGen-14b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anonymous192837192873/GraphGen-14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anonymous192837192873/GraphGen-14b

SGLang

How to use anonymous192837192873/GraphGen-14b 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 "anonymous192837192873/GraphGen-14b" \
    --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": "anonymous192837192873/GraphGen-14b",
		"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 "anonymous192837192873/GraphGen-14b" \
        --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": "anonymous192837192873/GraphGen-14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anonymous192837192873/GraphGen-14b with Docker Model Runner:
```
docker model run hf.co/anonymous192837192873/GraphGen-14b
```

GraphGen-14b / README.md

Anon

Add files using upload-large-folder tool

4405897 verified 3 days ago

preview code

raw

history blame contribute delete

806 Bytes

	---
	license: apache-2.0
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- anonymous-submission
	- graphgen
	- fine-tuned
	base_model: Qwen/Qwen2.5-Coder-14B-Instruct
	---

	# GraphGen-14b

	Anonymous submission accompanying a conference paper.

	Fine-tuned from `Qwen/Qwen2.5-Coder-14B-Instruct` on the companion
	`GraphGen` dataset to generate multi-agent workflow configurations from
	natural-language queries.

	## Quick start

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	repo = "anonymus192837192873/GraphGen-14b"
	tok = AutoTokenizer.from_pretrained(repo)
	model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="bfloat16", device_map="auto")
	```

	## Notes

	Released for anonymous peer review. Author and affiliation information
	is intentionally withheld.