Instructions to use Almawave/Velvet-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Almawave/Velvet-14B with Transformers:

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

pipe = pipeline("text-generation", model="Almawave/Velvet-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Almawave/Velvet-14B")
model = AutoModelForCausalLM.from_pretrained("Almawave/Velvet-14B")
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

vLLM

How to use Almawave/Velvet-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Almawave/Velvet-14B"
# 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-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Almawave/Velvet-14B

SGLang

How to use Almawave/Velvet-14B 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-14B" \
    --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-14B",
		"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-14B" \
        --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-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Almawave/Velvet-14B with Docker Model Runner:
```
docker model run hf.co/Almawave/Velvet-14B
```

Clarifications on the "llama" labeling for Velvet on Ollama

#11

by Kar0nte - opened Feb 24, 2025

Discussion

Kar0nte

Feb 24, 2025

•

edited Feb 26, 2025

Hi,

I noticed that the Velvet-2B/14B model by Almawave, described as developed from scratch and not derived from Llama or Mistral, is listed on Ollama with the label "model: llama." This seems to contradict the official documentation, which states that Velvet is an independent base model.

My question is:

Is this a labeling error on Ollama?

Or could it be related to technical compatibility with frameworks like llama.cpp?

Thank you in advance for any clarification!

vincenzo-sciacca-fox

Almawave org Feb 26, 2025

Hi, we used llmapa.cpp to make our model compatible with the Ollama framework. The 'llama' label you mentioned is not related to the Velvet neural architecture itself, but rather depends on how Ollama represents our model.
Thank you for you interest in Velvet

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