Instructions to use oxyapi/oxy-1-small-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oxyapi/oxy-1-small-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="oxyapi/oxy-1-small-GGUF") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("oxyapi/oxy-1-small-GGUF", dtype="auto") - llama-cpp-python
How to use oxyapi/oxy-1-small-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="oxyapi/oxy-1-small-GGUF", filename="oxy-1-small.F16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use oxyapi/oxy-1-small-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf oxyapi/oxy-1-small-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf oxyapi/oxy-1-small-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf oxyapi/oxy-1-small-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf oxyapi/oxy-1-small-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 oxyapi/oxy-1-small-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf oxyapi/oxy-1-small-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 oxyapi/oxy-1-small-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf oxyapi/oxy-1-small-GGUF:Q4_K_M
Use Docker
docker model run hf.co/oxyapi/oxy-1-small-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use oxyapi/oxy-1-small-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "oxyapi/oxy-1-small-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": "oxyapi/oxy-1-small-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/oxyapi/oxy-1-small-GGUF:Q4_K_M
- SGLang
How to use oxyapi/oxy-1-small-GGUF 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 "oxyapi/oxy-1-small-GGUF" \ --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": "oxyapi/oxy-1-small-GGUF", "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 "oxyapi/oxy-1-small-GGUF" \ --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": "oxyapi/oxy-1-small-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use oxyapi/oxy-1-small-GGUF with Ollama:
ollama run hf.co/oxyapi/oxy-1-small-GGUF:Q4_K_M
- Unsloth Studio
How to use oxyapi/oxy-1-small-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 oxyapi/oxy-1-small-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 oxyapi/oxy-1-small-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for oxyapi/oxy-1-small-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use oxyapi/oxy-1-small-GGUF with Docker Model Runner:
docker model run hf.co/oxyapi/oxy-1-small-GGUF:Q4_K_M
- Lemonade
How to use oxyapi/oxy-1-small-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull oxyapi/oxy-1-small-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.oxy-1-small-GGUF-Q4_K_M
List all available models
lemonade list
What character format use this model?
It doesn't work well in all offline Llm applications because writes repetitive, incomprehensible confusion at the end of the dialogues.
In the "Sapce" application tested here, it offers a great, enjoyable chat, but there is no character information, but it works incorrectly in LM studio and Kobold AI.
One thing is certain, the character description containing the normal narrative description does not correspond to this model, because it easily switches roles.
The users need, should know what character format and instructions and settings this model works well with.
Hi, yes it seems that there are repetition problems that I have not managed to resolve, it is better to use version Q8_0 which is the one used in the demo, I have never role-played with LLM but according to my dataset your prompt system must contain in order;
A description of the context, the place, the time, the world, the other characters with whom he must interact, his limitations
A list of the model's characteristics, precisely describe their body, their way of speaking, their clothes, etc.
[Optional] After the system prompt, insert a first message that you will write while interpreting the character that the model must play
then it should be ready to use if that doesn't work try other prompt system "formats" there are specific sites for that it seems to me I think you won't miss any haha, good luck and thank you for opening this discussion.
Just wanted to add that putting this stop string under advanced formatting fixed it in my case.
[ "[", " ["]