Instructions to use CEIA-RL/qwen3-4b-dw-lr-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CEIA-RL/qwen3-4b-dw-lr-dpo with Transformers:

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

pipe = pipeline("text-generation", model="CEIA-RL/qwen3-4b-dw-lr-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CEIA-RL/qwen3-4b-dw-lr-dpo")
model = AutoModelForCausalLM.from_pretrained("CEIA-RL/qwen3-4b-dw-lr-dpo")
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 CEIA-RL/qwen3-4b-dw-lr-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CEIA-RL/qwen3-4b-dw-lr-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CEIA-RL/qwen3-4b-dw-lr-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CEIA-RL/qwen3-4b-dw-lr-dpo

SGLang

How to use CEIA-RL/qwen3-4b-dw-lr-dpo 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 "CEIA-RL/qwen3-4b-dw-lr-dpo" \
    --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": "CEIA-RL/qwen3-4b-dw-lr-dpo",
		"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 "CEIA-RL/qwen3-4b-dw-lr-dpo" \
        --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": "CEIA-RL/qwen3-4b-dw-lr-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CEIA-RL/qwen3-4b-dw-lr-dpo with Docker Model Runner:
```
docker model run hf.co/CEIA-RL/qwen3-4b-dw-lr-dpo
```

Model Card for qwen3-4b-dw-lr-dpo

This model is a fine-tuned version of cemig-temp/qwen3-4b-dw-lr. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="CEIA-RL/qwen3-4b-dw-lr-dpo", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with Online DPO, a method introduced in Direct Language Model Alignment from Online AI Feedback.

Framework versions

TRL: 0.29.0
Transformers: 4.57.6
Pytorch: 2.10.0
Datasets: 4.7.0
Tokenizers: 0.22.2

Citations

Cite Online DPO as:

@article{guo2024direct,
    title        = {{Direct Language Model Alignment from Online AI Feedback}},
    author       = {Shangmin Guo and Biao Zhang and Tianlin Liu and Tianqi Liu and Misha Khalman and Felipe Llinares and Alexandre Ram{'{e}} and Thomas Mesnard and Yao Zhao and Bilal Piot and Johan Ferret and Mathieu Blondel},
    year         = 2024,
    eprint       = {arXiv:2402.04792}
}

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}

Downloads last month: 291

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for CEIA-RL/qwen3-4b-dw-lr-dpo

Base model

cemig-temp/qwen3-4b-dw-lr

Finetuned

(5)

this model

Paper for CEIA-RL/qwen3-4b-dw-lr-dpo

Direct Language Model Alignment from Online AI Feedback

Paper • 2402.04792 • Published Feb 7, 2024 • 35