Instructions to use VinitT/Qwen2-0.5B-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VinitT/Qwen2-0.5B-DPO with Transformers:

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

pipe = pipeline("text-generation", model="VinitT/Qwen2-0.5B-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VinitT/Qwen2-0.5B-DPO")
model = AutoModelForCausalLM.from_pretrained("VinitT/Qwen2-0.5B-DPO", 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 VinitT/Qwen2-0.5B-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VinitT/Qwen2-0.5B-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": "VinitT/Qwen2-0.5B-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VinitT/Qwen2-0.5B-DPO

SGLang

How to use VinitT/Qwen2-0.5B-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 "VinitT/Qwen2-0.5B-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": "VinitT/Qwen2-0.5B-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 "VinitT/Qwen2-0.5B-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": "VinitT/Qwen2-0.5B-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VinitT/Qwen2-0.5B-DPO with Docker Model Runner:
```
docker model run hf.co/VinitT/Qwen2-0.5B-DPO
```

Model Card for Model ID

Model Details

Base Model: Qwen2-0.5B
Fine-tuning Method: Direct Preference Optimization (DPO)
Framework: Unsloth
Quantization: 4-bit QLoRA (during training)

Uses

from transformers import AutoTokenizer
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "VinitT/Qwen2-0.5B-DPO",
    dtype = None,
    load_in_4bit = False,
)

messages = [{"role": "user", "content": "Hello,how can i develop a habit of drawing daily?"}]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)
inputs = {k: v.to(model.device) for k, v in inputs.items()}

# Generate
outputs = model.generate(
    **inputs,
    max_new_tokens=100,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)
# Decode only the new response (not the prompt)
prompt_len = inputs["input_ids"].shape[-1]
response = tokenizer.decode(outputs[0][prompt_len:], skip_special_tokens=True)

print(response.strip())

Downloads last month: 6

Safetensors

Model size

0.5B params

Tensor type

F32

F16

Model tree for VinitT/Qwen2-0.5B-DPO

Base model

Qwen/Qwen2-0.5B

Finetuned

Qwen/Qwen2-0.5B-Instruct

Quantized

(90)

this model

VinitT
/

Qwen2-0.5B-DPO

Model Card for Model ID

Model Details

Uses

Model tree for VinitT/Qwen2-0.5B-DPO

Dataset used to train VinitT/Qwen2-0.5B-DPO