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

Libraries

How to use SistInf/Velvet-2B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SistInf/Velvet-2B-GGUF", dtype="auto")

llama-cpp-python

How to use SistInf/Velvet-2B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SistInf/Velvet-2B-GGUF",
	filename="Velvet-2B-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SistInf/Velvet-2B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SistInf/Velvet-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SistInf/Velvet-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SistInf/Velvet-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SistInf/Velvet-2B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SistInf/Velvet-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SistInf/Velvet-2B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SistInf/Velvet-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SistInf/Velvet-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SistInf/Velvet-2B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use SistInf/Velvet-2B-GGUF with Ollama:
```
ollama run hf.co/SistInf/Velvet-2B-GGUF:Q4_K_M
```

Unsloth Studio

How to use SistInf/Velvet-2B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SistInf/Velvet-2B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SistInf/Velvet-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SistInf/Velvet-2B-GGUF to start chatting

How to use SistInf/Velvet-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SistInf/Velvet-2B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SistInf/Velvet-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SistInf/Velvet-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SistInf/Velvet-2B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SistInf/Velvet-2B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use SistInf/Velvet-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/SistInf/Velvet-2B-GGUF:Q4_K_M
```

Lemonade

How to use SistInf/Velvet-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SistInf/Velvet-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Velvet-2B-GGUF-Q4_K_M

List all available models

lemonade list

DESCRIPTION

This model does not represent the intended quality of the original product.

To perform this quantization, we started with llama.cpp as our base, modifying the file convert_hf_to_gguf_update.py to support this model. For modifying this file, we based our work on what was seen in the PR https://github.com/ggerganov/llama.cpp/pull/11716.

Note: As of today, llama.cpp does not support this model or this chat template https://github.com/ggerganov/llama.cpp/pull/11716.

PROMPT FORMAT

Basic prompt format:

<s><instruction>{prompt}</instruction>

Prompt format with system message:

<s><instruction>{system_prompt}
{prompt}</instruction>

DOWNLOAD

Quant	Link
BF16	Velvet-2B-BF16
F16	Velvet-2B-F16.gguf
Q4_K_M	Velvet-2B-Q4_K_M
Q4_K_S	Velvet-2B-Q4_K_S
Q5_K_M	Velvet-2B-Q5_K_M
Q6_K	Velvet-2B-Q6_K.gguf
Q8_0	Velvet-2B-Q8_0.gguf

Original Model: https://huggingface.co/Almawave/Velvet-2B

License

Velvet-2B and Velvet-2B are made available under the Apache 2.0 license

Downloads last month: 106

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SistInf/Velvet-2B-GGUF

Base model

Almawave/Velvet-2B

Quantized

(3)

this model