Instructions to use SatoshiManjoro/MiniManjoro-25M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SatoshiManjoro/MiniManjoro-25M with RWKV:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SatoshiManjoro/MiniManjoro-25M with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SatoshiManjoro/MiniManjoro-25M
# Run inference directly in the terminal:
llama cli -hf SatoshiManjoro/MiniManjoro-25M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SatoshiManjoro/MiniManjoro-25M
# Run inference directly in the terminal:
llama cli -hf SatoshiManjoro/MiniManjoro-25M

Build 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 SatoshiManjoro/MiniManjoro-25M
# Run inference directly in the terminal:
./build/bin/llama cli -hf SatoshiManjoro/MiniManjoro-25M

Use Docker

docker model run hf.co/SatoshiManjoro/MiniManjoro-25M

Llama new
LM Studio
Jan

vLLM

How to use SatoshiManjoro/MiniManjoro-25M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SatoshiManjoro/MiniManjoro-25M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SatoshiManjoro/MiniManjoro-25M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SatoshiManjoro/MiniManjoro-25M

Ollama
How to use SatoshiManjoro/MiniManjoro-25M with Ollama:
```
ollama run hf.co/SatoshiManjoro/MiniManjoro-25M
```
Unsloth Desktop
Docker Model Runner
How to use SatoshiManjoro/MiniManjoro-25M with Docker Model Runner:
```
docker model run hf.co/SatoshiManjoro/MiniManjoro-25M
```

Lemonade

How to use SatoshiManjoro/MiniManjoro-25M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SatoshiManjoro/MiniManjoro-25M

Run and chat with the model

lemonade run user.MiniManjoro-25M-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

"readme.md translated into both Russian and English"/"readme.md переведенный и на русский и на английский"

by SatoshiManjoro - opened 6 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+205

-4

SatoshiManjoro

Owner 6 days ago

ОБНОВЛЕННЫЙ README.MD И БОЛЕЕ ДЕТАЛЬНОЕ ОПИСАНИЕ:

Особенности архитектуры
Характеристики модели
Отличия от классического обучения LLM
Установка и зависимости
Порядок запуска (Pipeline)
Разбор структуры проекта и скриптов
Как проходило обучение
Инференс и тестирование (Чат)
Экспорт в формат GGUF
Лицензия

Следующая цель: модель на 200 миллионов параметров

UPDATED README.MD AND A MORE DETAILED DESCRIPTION:

Architecture features
Model specifications
Differences from classical LLM training
Installation and dependencies
Launch order (Pipeline)
Breakdown of the project structure and scripts
How training was done
Inference and testing (Chat)
Export to GGUF format
License

Next goal: a 200-million-parameter model

"readme.md translated into both Russian and English"/"readme.md переведенный и на русский и на английский"6bd4611c

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment