Instructions to use blueprintninja/Unreal-Blueprint-Assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use blueprintninja/Unreal-Blueprint-Assistant with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("undefined") model.load_adapter("blueprintninja/Unreal-Blueprint-Assistant", set_active=True) - llama-cpp-python
How to use blueprintninja/Unreal-Blueprint-Assistant with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="blueprintninja/Unreal-Blueprint-Assistant", filename="gguf-unreal-rope-4k-5epochsmodel-unsloth.Q8_0.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use blueprintninja/Unreal-Blueprint-Assistant with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0 # Run inference directly in the terminal: llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0 # Run inference directly in the terminal: llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0
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 blueprintninja/Unreal-Blueprint-Assistant:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0
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 blueprintninja/Unreal-Blueprint-Assistant:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0
Use Docker
docker model run hf.co/blueprintninja/Unreal-Blueprint-Assistant:Q8_0
- LM Studio
- Jan
- vLLM
How to use blueprintninja/Unreal-Blueprint-Assistant with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "blueprintninja/Unreal-Blueprint-Assistant" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "blueprintninja/Unreal-Blueprint-Assistant", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/blueprintninja/Unreal-Blueprint-Assistant:Q8_0
- Ollama
How to use blueprintninja/Unreal-Blueprint-Assistant with Ollama:
ollama run hf.co/blueprintninja/Unreal-Blueprint-Assistant:Q8_0
- Unsloth Studio
How to use blueprintninja/Unreal-Blueprint-Assistant 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 blueprintninja/Unreal-Blueprint-Assistant 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 blueprintninja/Unreal-Blueprint-Assistant to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for blueprintninja/Unreal-Blueprint-Assistant to start chatting
- Docker Model Runner
How to use blueprintninja/Unreal-Blueprint-Assistant with Docker Model Runner:
docker model run hf.co/blueprintninja/Unreal-Blueprint-Assistant:Q8_0
- Lemonade
How to use blueprintninja/Unreal-Blueprint-Assistant with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull blueprintninja/Unreal-Blueprint-Assistant:Q8_0
Run and chat with the model
lemonade run user.Unreal-Blueprint-Assistant-Q8_0
List all available models
lemonade list
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0# Run inference directly in the terminal:
llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0Use 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 blueprintninja/Unreal-Blueprint-Assistant:Q8_0# Run inference directly in the terminal:
./llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0Build 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 blueprintninja/Unreal-Blueprint-Assistant:Q8_0# Run inference directly in the terminal:
./build/bin/llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0Use Docker
docker model run hf.co/blueprintninja/Unreal-Blueprint-Assistant:Q8_0Model Details This model is a text-to-text transformer that can generate Unreal Engine blueprints from natural language questions. It was trained on a custom dataset of question/answer pairs about Unreal Engine blueprints, using the T5 architecture3. The model can also create new blueprints that are not in the original dataset, using its own logic.
Intended Use This model is intended for educational and entertainment purposes only. It can be used by Unreal Engine enthusiasts, game developers, or students who want to learn more about blueprints and how to create them. The model is not intended to replace professional guidance or documentation on Unreal Engine development.
Limitations and Bias This model has some limitations and potential biases that users should be aware of:
The model is based on a custom dataset that may not cover all aspects of Unreal Engine blueprints or reflect the diversity of natural language expressions. The model may not be able to answer some questions correctly or generate valid blueprints for some scenarios. The model may exhibit some hallucinations or inconsistencies when generating new blueprints that are not in the original dataset. The model may not follow the best practices or conventions of Unreal Engine development. The model may also generate blueprints that are impractical, inefficient, or harmful. The model may inherit some biases from the data or the pre-trained T5 model that it is based on. The model may favor certain types of blueprints, questions, or answers over others. The model may also reflect some stereotypes or prejudices that are present in the data or the language.
- Downloads last month
- 66
8-bit
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0# Run inference directly in the terminal: llama-cli -hf blueprintninja/Unreal-Blueprint-Assistant:Q8_0