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
```

Quantization Q2_K

by sharonsky - opened Feb 3, 2025

Discussion

sharonsky

Feb 3, 2025

I want to quantize the model in Q2_K gguf but there is not enough merges.txt. Please add merges.txt or tokenizer.model

andreatironi

Feb 3, 2025

Where can i find gguf file?

sharonsky

Feb 6, 2025

Where can i find gguf file?

gguf file is created, but I can't add a dictionary there, because it should be a SentencePiece. To convert to SentencePiece, I need merges.txt. And without a dictionary, the gguf file is useless. I can upload it, maybe someone will finish it

andreatironi

Feb 6, 2025

In comment #5 probably there is a solution.

f-buciuni

Almawave org Feb 7, 2025

A pull request in the llama.cpp repository (https://github.com/ggerganov/llama.cpp/pull/11716) has already been submitted to address this issue and is currently under review. You can refer to the fork used for the pull request or wait for the marge to convert the model to GGUF format and to quantize it using the allowed methods (i.e. Q2_K).

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