theprint/gamedev_alpaca
Viewer • Updated • 76.1k • 19 • 1
How to use theprint/phi-3-mini-4k-gamedev with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("theprint/phi-3-mini-4k-gamedev", device_map="auto")How to use theprint/phi-3-mini-4k-gamedev with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf theprint/phi-3-mini-4k-gamedev:Q4_K_M # Run inference directly in the terminal: llama cli -hf theprint/phi-3-mini-4k-gamedev:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf theprint/phi-3-mini-4k-gamedev:Q4_K_M # Run inference directly in the terminal: llama cli -hf theprint/phi-3-mini-4k-gamedev:Q4_K_M
# 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 theprint/phi-3-mini-4k-gamedev:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf theprint/phi-3-mini-4k-gamedev:Q4_K_M
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 theprint/phi-3-mini-4k-gamedev:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf theprint/phi-3-mini-4k-gamedev:Q4_K_M
docker model run hf.co/theprint/phi-3-mini-4k-gamedev:Q4_K_M
How to use theprint/phi-3-mini-4k-gamedev with Ollama:
ollama run hf.co/theprint/phi-3-mini-4k-gamedev:Q4_K_M
How to use theprint/phi-3-mini-4k-gamedev with Docker Model Runner:
docker model run hf.co/theprint/phi-3-mini-4k-gamedev:Q4_K_M
How to use theprint/phi-3-mini-4k-gamedev with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull theprint/phi-3-mini-4k-gamedev:Q4_K_M
lemonade run user.phi-3-mini-4k-gamedev-Q4_K_M
lemonade list
This model was fine tuned on the things that go into creating games and building game studios, except for the coding part. Instead of code, this model focuses on things like project management, marketing, community, outsourcing and all those other things that can't be done in a game engine.
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
4-bit
5-bit
6-bit
8-bit
16-bit