How to use from
llama.cpp
Install from brew
brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Havmand/minillama
# Run inference directly in the terminal:
llama-cli -hf Havmand/minillama
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Havmand/minillama
# Run inference directly in the terminal:
llama-cli -hf Havmand/minillama
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 Havmand/minillama
# Run inference directly in the terminal:
./llama-cli -hf Havmand/minillama
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 Havmand/minillama
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Havmand/minillama
Use Docker
docker model run hf.co/Havmand/minillama
Quick Links

minillama

Description

minillama is a minimal Large Language Model using the Llama architecture and distributed in the GGUF format.

The purpose of the model is to be small and technically qualify as a model that can be loaded with llama.cpp without causing an error. I originally created this model because I needed a small model for my unit tests of Python code that used llama-cpp-python.

The model can technically be used for inference, but the output produced is a close to useless as you can get. Tokens per second is nice though, at around 1000 tokens per second on an Apple M2 Pro.

To reduce file size, the model is quantized using Q2_K.

The model contains 4.26 million parameters and is 3.26 MiB.

As for the vocabulary, the model uses the llama vocabulary provided by llama.cpp (SHA512: 38a5acf305050422882044df0acc97e5ae992ed19b2838b3b58ebbbb1f61c59bfc12a6f686a724aed32227045806e4dd46aadf9822155d1169455fa56d38fbc2)

The training corpus consists of a space and a newline:

00000000  20 0a                                             | .|
00000002

Finally, the model was build using llama.cpp's train-text-from-scratch (from commit 97c1549808d2742d37584a3c9df28154bdf34417). The command used was:

./train-text-from-scratch \
        --vocab-model models/ggml-vocab-llama.gguf \
        --ctx 1 --embd 64 --head 1 --layer 1 \
        --checkpoint-in  chk-minillama-LATEST.gguf \
        --checkpoint-out chk-minillama-ITERATION.gguf \
        --model-out ggml-minillama-f32-ITERATION.gguf \
        --train-data "training.txt" \
        -t 6 -b 16 --seed 1 --adam-iter 1 \
        --no-checkpointing

Quantization happened using ./quantize ggml-minillama-f32-LATEST.gguf 10.

These files were quantized using hardware kindly provided by me.

Downloads last month
22
GGUF
Model size
4.26M params
Architecture
llama
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. ๐Ÿ™‹ Ask for provider support