Instructions to use Tuwhy/Qwen3-4B-OPSA-Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tuwhy/Qwen3-4B-OPSA-Code with Transformers:

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

pipe = pipeline("text-generation", model="Tuwhy/Qwen3-4B-OPSA-Code")
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("Tuwhy/Qwen3-4B-OPSA-Code")
model = AutoModelForCausalLM.from_pretrained("Tuwhy/Qwen3-4B-OPSA-Code", 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 Tuwhy/Qwen3-4B-OPSA-Code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tuwhy/Qwen3-4B-OPSA-Code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tuwhy/Qwen3-4B-OPSA-Code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tuwhy/Qwen3-4B-OPSA-Code

SGLang

How to use Tuwhy/Qwen3-4B-OPSA-Code 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 "Tuwhy/Qwen3-4B-OPSA-Code" \
    --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": "Tuwhy/Qwen3-4B-OPSA-Code",
		"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 "Tuwhy/Qwen3-4B-OPSA-Code" \
        --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": "Tuwhy/Qwen3-4B-OPSA-Code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tuwhy/Qwen3-4B-OPSA-Code with Docker Model Runner:
```
docker model run hf.co/Tuwhy/Qwen3-4B-OPSA-Code
```

Qwen3-4B-OPSA-Code / README.md

Tuwhy

Upload OPSA code checkpoint step 259

631e4fd verified about 1 month ago

preview code

Raw History Blame Contribute Delete

1.85 kB

metadata

library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
base_model: Qwen/Qwen3-4B
base_model_relation: finetune
arxiv: 2608.31046
tags:
  - opsa
  - code
  - text-generation

Qwen3-4B-OPSA-Code

This repository contains the code-domain checkpoint of Qwen/Qwen3-4B trained with On-Policy Self-Adaptation (OPSA).

Checkpoint: step 259 (260 optimizer updates; zero-based checkpoint numbering).
Format: full model weights in BF16 Safetensors, with configuration and tokenizer files.
License: Apache 2.0, following the base model.

Paper · Code · Collection

Usage

Install torch, accelerate, and transformers>=4.57.1.

Use the Qwen chat template with enable_thinking=False.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Tuwhy/Qwen3-4B-OPSA-Code"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
messages = [{"role": "user", "content": "Write a Python function that checks whether a string is a palindrome."}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt", enable_thinking=False,
).to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=2048,
    do_sample=True,
    temperature=0.7,
    top_p=0.8,
    top_k=20,
)
print(tokenizer.decode(outputs[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))