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 nahcmon/My-First-Model# Run inference directly in the terminal:
llama cli -hf nahcmon/My-First-ModelBuild from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf nahcmon/My-First-Model# Run inference directly in the terminal:
./build/bin/llama cli -hf nahcmon/My-First-ModelUse Docker
docker model run hf.co/nahcmon/My-First-ModelQuick Links
This is my very first fully self trained LLM that outputs something that is actually related to the input. Note that this is only a ~170M parameter model trained exclusively on the TinyStories dataset, so do not expect any record-breaking outputs. Just a dude on the internet trying to make something.
- Downloads last month
- 11
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 nahcmon/My-First-Model# Run inference directly in the terminal: llama cli -hf nahcmon/My-First-Model