Instructions to use HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3 with Transformers:

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

pipe = pipeline("text-generation", model="HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3")
model = AutoModelForCausalLM.from_pretrained("HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3

SGLang

How to use HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3 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 "HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3" \
    --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": "HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3",
		"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 "HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3" \
        --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": "HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3 with Docker Model Runner:
```
docker model run hf.co/HuggingJin/resail-qwen3-8b-alfworld-sdpo-c3
```

SDPO + ReSAIL — Qwen3-8B — ALFWorld — Cycle 3

This repository contains the publicly released Cycle 3 checkpoint of SDPO + ReSAIL, based on Qwen/Qwen3-8B and trained on ALFWorld.

ReSAIL augments iterative agent self-distillation with trajectory-balanced selective distillation and privileged retention.

Code and documentation: ShengjieJin/ReSAIL
All checkpoints: ReSAIL Collection

Evaluation

Reported three-decoding-seed mean: ALFWorld ID 82.0%; ALFWorld OOD 75.3%.
The reported variation is across decoding seeds, not independent training seeds.
Thinking mode was disabled for the text-agent experiments.

Lineage

Base model: Qwen/Qwen3-8B
Training task: ALFWorld
Method: SDPO + ReSAIL
Deployment cycle: 3

For environment setup, task data, training, and evaluation instructions, see the ReSAIL repository. The paper link and citation will be added when available.