Instructions to use Almawave/Velvet-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Almawave/Velvet-2B with Transformers:

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

pipe = pipeline("text-generation", model="Almawave/Velvet-2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Almawave/Velvet-2B")
model = AutoModelForCausalLM.from_pretrained("Almawave/Velvet-2B")
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 Almawave/Velvet-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Almawave/Velvet-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Almawave/Velvet-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Almawave/Velvet-2B

SGLang

How to use Almawave/Velvet-2B 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 "Almawave/Velvet-2B" \
    --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": "Almawave/Velvet-2B",
		"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 "Almawave/Velvet-2B" \
        --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": "Almawave/Velvet-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Almawave/Velvet-2B with Docker Model Runner:
```
docker model run hf.co/Almawave/Velvet-2B
```

Ollama/llama.cpp support

by dpreti - opened Feb 12, 2025

Discussion

dpreti

Almawave org Feb 12, 2025

•

edited Feb 12, 2025

We observed that at the moment the model is not served correctly with Ollama and llama.cpp .

We are currently investigating the reasons behind this unexpected behavior.
In the meanwhile we strongly suggest to serve the model using vLLM or the Transformer library as showed in the model card.

dpreti changed discussion title from Ollama support to Ollama/llama.cpp support Feb 12, 2025

dpreti

Almawave org Feb 20, 2025

Velvet-2B model has been released on the ollama library. It can be used directly with the command:

ollama run Almawave/velvet:2B

All the versions corresponding to different "tags" are available and can be found here:
https://ollama.com/Almawave/Velvet

dpreti changed discussion status to closed Feb 20, 2025

manubot

May 13, 2025

what about the command for llama.cpp?

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