Instructions to use HuggingJin/resail-qwen3-4b-textcraft-oel-c3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingJin/resail-qwen3-4b-textcraft-oel-c3 with Transformers:

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

pipe = pipeline("text-generation", model="HuggingJin/resail-qwen3-4b-textcraft-oel-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-qwen3-4b-textcraft-oel-c3")
model = AutoModelForCausalLM.from_pretrained("HuggingJin/resail-qwen3-4b-textcraft-oel-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-qwen3-4b-textcraft-oel-c3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingJin/resail-qwen3-4b-textcraft-oel-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-qwen3-4b-textcraft-oel-c3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingJin/resail-qwen3-4b-textcraft-oel-c3

SGLang

How to use HuggingJin/resail-qwen3-4b-textcraft-oel-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-qwen3-4b-textcraft-oel-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-qwen3-4b-textcraft-oel-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-qwen3-4b-textcraft-oel-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-qwen3-4b-textcraft-oel-c3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingJin/resail-qwen3-4b-textcraft-oel-c3 with Docker Model Runner:
```
docker model run hf.co/HuggingJin/resail-qwen3-4b-textcraft-oel-c3
```

HuggingJin commited on 17 days ago

Commit

b8eb506

verified ·

1 Parent(s): 0843bfa

Update public ReSAIL model card and repository links

Browse files

Files changed (1) hide show

README.md +7 -3

README.md CHANGED Viewed

@@ -12,8 +12,12 @@ tags:
 # OEL + ReSAIL — Qwen3-4B — TextCraft — Cycle 3
-This is a private staging copy of a Cycle 3 checkpoint from an anonymous research submission.
-It is not yet intended for redistribution or citation.
 ## Evaluation
@@ -28,4 +32,4 @@ It is not yet intended for redistribution or citation.
 - Method: `OEL + ReSAIL`
 - Deployment cycle: 3
-Detailed training data, prompts, evaluation commands, and limitations will be added before any public release.

 # OEL + ReSAIL — Qwen3-4B — TextCraft — Cycle 3
+This repository contains the publicly released **Cycle 3** checkpoint of **OEL + ReSAIL**, based on **Qwen/Qwen3-4B** and trained on **TextCraft**.
+ReSAIL augments iterative agent self-distillation with trajectory-balanced selective distillation and privileged retention.
+**Code and documentation:** [ShengjieJin/ReSAIL](https://github.com/ShengjieJin/ReSAIL)
+**All checkpoints:** [ReSAIL Collection](https://huggingface.co/collections/HuggingJin/resail-6ab8e06426ca99d03aabfa0f)
 ## Evaluation
 - Method: `OEL + ReSAIL`
 - Deployment cycle: 3
+For environment setup, task data, training, and evaluation instructions, see the [ReSAIL repository](https://github.com/ShengjieJin/ReSAIL). The paper link and citation will be added when available.