Instructions to use yuyangbai/graphdancer-dpo-iter1-seed167 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuyangbai/graphdancer-dpo-iter1-seed167 with Transformers:

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

pipe = pipeline("text-generation", model="yuyangbai/graphdancer-dpo-iter1-seed167")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yuyangbai/graphdancer-dpo-iter1-seed167")
model = AutoModelForCausalLM.from_pretrained("yuyangbai/graphdancer-dpo-iter1-seed167", device_map="auto")
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 Settings

vLLM

How to use yuyangbai/graphdancer-dpo-iter1-seed167 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuyangbai/graphdancer-dpo-iter1-seed167"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuyangbai/graphdancer-dpo-iter1-seed167",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yuyangbai/graphdancer-dpo-iter1-seed167

SGLang

How to use yuyangbai/graphdancer-dpo-iter1-seed167 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 "yuyangbai/graphdancer-dpo-iter1-seed167" \
    --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": "yuyangbai/graphdancer-dpo-iter1-seed167",
		"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 "yuyangbai/graphdancer-dpo-iter1-seed167" \
        --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": "yuyangbai/graphdancer-dpo-iter1-seed167",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yuyangbai/graphdancer-dpo-iter1-seed167 with Docker Model Runner:
```
docker model run hf.co/yuyangbai/graphdancer-dpo-iter1-seed167
```

GraphDancer-DPO Iter-1 (seed 167) — best single-seed Rouge-L

This is the highest-Rouge-L single-seed result from the GraphDancer iter-1 DPO refinement of yuyangbai/GraphDancer-Qwen2.5-3B-Instruct-Curriculum-PPO.

Headline numbers (full GRBench eval, 890 queries, T=0.7 single-sample)

domain	N	EM	Rouge-L
amazon	200	0.4350	0.4983
biomedical	270	0.2667	0.3279
goodreads	240	0.4500	0.4924
legal	180	0.4167	0.4570
AVG	—	0.3923	0.4439

vs paper PPO baseline 0.4062 → +0.0377 R-L AVG (single seed).

Distribution context (across 11 seeds with the same recipe)

All-11 mean R-L AVG: 0.4265 ± 0.0079
This seed (167) is the maximum (0.4439); seed 109 is the minimum (0.4156).
1-sample t-test of all-11 mean vs paper-PPO 0.4062: t=8.48, df=10, p<0.001.

Recipe

Base = π_ref = yuyangbai/GraphDancer-Qwen2.5-3B-Instruct-Curriculum-PPO
Phase 0: K=8 trajectories sampled from π_ref (verl + vLLM, T=1.0, top_p=0.95, max_turns=10)
Pair builder: lex tuple v1 = (em, eh, vf, -loop, -invalid_tool, -n_graph_rounds), strategy extreme
Trainer: TRL 0.19.1 DPOTrainer (subclass with agent-token mask), β=0.1, lr=2e-7, 100 steps, global batch 64, warmup 0.05
Curriculum: paper-faithful E2HGaussian (q=[0.5,0.5,0], η 0.2→0.8, β=3, σ=0.75)
Seed: 167

See dpo_iter1_full_config.md and dpo_iter1_top5_summary.md in the GraphDancer-Codebases repo for full details and the 11-seed distribution.

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

F32

Model tree for yuyangbai/graphdancer-dpo-iter1-seed167

Base model

yuyangbai/GraphDancer-Qwen2.5-3B-Instruct-Curriculum-PPO

Finetuned

(1)

this model