How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf North-ML1/proto-mini# Run inference directly in the terminal:
llama cli -hf North-ML1/proto-miniUse 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 North-ML1/proto-mini# Run inference directly in the terminal:
./llama-cli -hf North-ML1/proto-miniBuild 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 North-ML1/proto-mini# Run inference directly in the terminal:
./build/bin/llama-cli -hf North-ML1/proto-miniUse Docker
docker model run hf.co/North-ML1/proto-miniQuick Links
Proto Mini - Random models that output text
Proto-mini are small GGUF files that output text - without needing to be trained on huge corpus'. Via lite pretraining - random init - and more, we have achieved quality that beats init models. If you cpt on these GGUF's via Unsloth Studio, you get sequence level text generations.
It reaches speeds on 640 tok/s on the content in init.txt, random tokens with c at the start.
It already has the vocab - it just needs to know what to use.
- Downloads last month
- 95
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf North-ML1/proto-mini# Run inference directly in the terminal: llama cli -hf North-ML1/proto-mini