Instructions to use thangvip/vwen-0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thangvip/vwen-0.5 with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thangvip/vwen-0.5")
model = AutoModelForCausalLM.from_pretrained("thangvip/vwen-0.5")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use thangvip/vwen-0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thangvip/vwen-0.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thangvip/vwen-0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thangvip/vwen-0.5

SGLang

How to use thangvip/vwen-0.5 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 "thangvip/vwen-0.5" \
    --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": "thangvip/vwen-0.5",
		"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 "thangvip/vwen-0.5" \
        --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": "thangvip/vwen-0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thangvip/vwen-0.5 with Docker Model Runner:
```
docker model run hf.co/thangvip/vwen-0.5
```

Question about thangvip/vwen-0.5 and its base model

by dqdw - opened Feb 28

Discussion

dqdw

Feb 28

Dear [Developer/Team],

I recently came across thangvip/vwen-0.5, and it has been very helpful in my project.

Before building on top of it, I would like to understand its connection with sail/Sailor-0.5B:

Direct Fine-tuning: Was sail/Sailor-0.5B the direct starting point for training thangvip/vwen-0.5?

Inheritance: Does it strictly inherit the architecture and weights of sail/Sailor-0.5B without merging or distilling from other models?

I just want to make sure I'm using it the right way.

I really appreciate your help.

Thanks again

thangvip

Owner Mar 31

@dqdw

Hi there,

Thank you for reaching out! I'm thrilled to hear that thangvip/vwen-0.5 has been helpful in your project.

To answer your questions directly:

Direct Fine-tuning: Yes, sail/Sailor-0.5B was the direct starting point for training thangvip/vwen-0.5.

Inheritance: It strictly inherits the architecture and weights of sail/Sailor-0.5B. The model was trained directly on it, and there was no merging or distillation from any other models involved in its creation.

I hope this clarifies things and gives you the confidence you need to continue building on top of it. Please don't hesitate to reach out if you have any other questions.

Best regards,
Le Vo Quyet Thang

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment