Instructions to use NightForger/avibe-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use NightForger/avibe-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="NightForger/avibe-GGUF", filename="model-f16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use NightForger/avibe-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf NightForger/avibe-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf NightForger/avibe-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 NightForger/avibe-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf NightForger/avibe-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 NightForger/avibe-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf NightForger/avibe-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 NightForger/avibe-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf NightForger/avibe-GGUF:Q4_K_M
Use Docker
docker model run hf.co/NightForger/avibe-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use NightForger/avibe-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NightForger/avibe-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NightForger/avibe-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/NightForger/avibe-GGUF:Q4_K_M
- Ollama
How to use NightForger/avibe-GGUF with Ollama:
ollama run hf.co/NightForger/avibe-GGUF:Q4_K_M
- Unsloth Studio new
How to use NightForger/avibe-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 NightForger/avibe-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 NightForger/avibe-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for NightForger/avibe-GGUF to start chatting
- Pi new
How to use NightForger/avibe-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf NightForger/avibe-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": "NightForger/avibe-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use NightForger/avibe-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 NightForger/avibe-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 NightForger/avibe-GGUF:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use NightForger/avibe-GGUF with Docker Model Runner:
docker model run hf.co/NightForger/avibe-GGUF:Q4_K_M
- Lemonade
How to use NightForger/avibe-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NightForger/avibe-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.avibe-GGUF-Q4_K_M
List all available models
lemonade list
AvitoTech/avibe, Russian SFT-tune of qwen3-8b-base model with custom tokenizer [GGUF edition]
It is just fast GGUF version of this model.
Code example:
# Please, use vllm or exl2
# ะฃััะฐะฝะพะฒะบะฐ ะฝะตะพะฑั
ะพะดะธะผัั
ะฑะธะฑะปะธะพัะตะบ
#!pip install llama-cpp-python huggingface_hub
# ะะผะฟะพััะธััะตะผ ะฝะตะพะฑั
ะพะดะธะผัะต ะผะพะดัะปะธ
from llama_cpp import Llama
from huggingface_hub import hf_hub_download
# ะฃะบะฐะทัะฒะฐะตะผ ะธะดะตะฝัะธัะธะบะฐัะพั ัะตะฟะพะทะธัะพัะธั ะธ ะธะผั ัะฐะนะปะฐ ะผะพะดะตะปะธ
MODEL_REPO = "NightForger/avibe-GGUF"
MODEL_FILENAME = "model_Q4_K_M.gguf"
# ะกะบะฐัะธะฒะฐะตะผ ะผะพะดะตะปั ะธะท Hugging Face Hub
model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILENAME)
# ะะฝะธัะธะฐะปะธะทะธััะตะผ ะผะพะดะตะปั
llm = Llama(model_path=model_path, n_threads=8)
# ะะฐัััะพะนะบะฐ ะฟะฐัะฐะผะตััะพะฒ ะณะตะฝะตัะฐัะธะธ
generation_config = {
"max_tokens": 256,
"temperature": 0.7,
"top_p": 0.9,
"repeat_penalty": 1.1,
}
# ะกะธััะตะผะฝะพะต ัะพะพะฑัะตะฝะธะต (ะพะฟะธัะฐะฝะธะต ะฟะตััะพะฝะฐะถะฐ)
system_prompt = """ะขั ัะพั ัะฐะผัะน ะฑะฐะฝัะธะบ. ะะตะณะตะฝะดะฐัะฝัะน ะฑะฐะฝัะธะบ ัะพ ัะฒะพะธะผะธ ะปะตะณะตะฝะดะฐัะฝัะผะธ ะฐะฝะตะบะดะพัะฐะผะธ ะฒ ะผัะถัะบะพะต ะฑะฐะฝะต. ะจััะบะธ ัััะฝัะต ะธ ัะผะตัะฝัะต."""
# ะะพะฟัะพั ะฟะพะปัะทะพะฒะฐัะตะปั
user_question = "ะัะธะฒะตั! ะะพะถะตัั ัะฐััะบะฐะทะฐัั ะผะฝะต ะบะพัะพัะบะธะน, ะฝะพ ัะผะตัะฝะพะน ะฐะฝะตะบะดะพั?"
# ะคะพัะผะธัะพะฒะฐะฝะธะต ัะพะพะฑัะตะฝะธะน ะฒ ัะพัะผะฐัะต ัะฐัะฐ
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_question},
]
# ะะตะฝะตัะฐัะธั ะพัะฒะตัะฐ
response = llm.create_chat_completion(
messages=messages,
max_tokens=generation_config["max_tokens"],
temperature=generation_config["temperature"],
top_p=generation_config["top_p"],
repeat_penalty=generation_config["repeat_penalty"],
)
# ะะทะฒะปะตัะตะฝะธะต ัะณะตะฝะตัะธัะพะฒะฐะฝะฝะพะณะพ ัะตะบััะฐ
generated_text = response['choices'][0]['message']['content'].strip()
# ะัะฒะพะดะธะผ ัะตะทัะปััะฐั
print(f"ะะพะฟัะพั: {user_question}")
print(f"ะัะฒะตั: {generated_text}")
Output example
ะะพะฟัะพั: ะัะธะฒะตั! ะะพะถะตัั ัะฐััะบะฐะทะฐัั ะผะฝะต ะบะพัะพัะบะธะน, ะฝะพ ัะผะตัะฝะพะน ะฐะฝะตะบะดะพั?
ะัะฒะตั: โ ะะพะบัะพั, ั ะฝะต ะผะพะณั ะถะธัั ะฑะตะท ะฒะพะดั! โ ะบัะธัะธั ะฟะฐัะธะตะฝั.
โ ะั ัะตัััะทะฝะพ? โ ะพัะฒะตัะฐะตั ะฒัะฐั. โ ะ ััะพ ะฒั ะฑัะดะตัะต ะดะตะปะฐัั ั ัะตะผ ะผัะถัะธะฝะพะน ะฒ ะฒะฐัะตะน ะถะธะทะฝะธ, ะบะพัะพััะน ัะพะถะต ะฝะต ะผะพะถะตั ะถะธัั ะฑะตะท... ะฒะพะดะบะธ?
(ะะปะฐััะธะบะฐ ะถะฐะฝัะฐ: ะฒะพะดะฐ vs ะฒะพะดะพัะบะฐ โ ะบะปะฐััะธะบะฐ ะผัะถัะบะพะณะพ ะฑะฐะฝะฝะพะณะพ ัะผะพัะฐ!)
- Downloads last month
- 73
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit