mlipy 0.1.31

Python-based Machine Learning Interface

mlipy

Pure Python-based Machine Learning Interface for multiple engines with multi-modal support.

Python HTTP Server/Client (including WebSocket streaming support) for:

• llama.cpp
• LangChain

Prerequisites

Debian/Ubuntu

sudo apt update -y
sudo apt install build-essential git curl libssl-dev libffi-dev pkg-config

Python

1. Install Python using internal repository:

sudo apt install python3.11 python3.11-dev python3.11-venv

2. Install Python using external repository:

sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt update -y
sudo apt install python3.11 python3.11-dev python3.11-venv

llama.cpp

cd ~
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j

Run Development Server

Setup virtualenv and install requirements:

git clone https://github.com/mtasic85/mlipy.git
cd mlipy

python3.11 -m venv venv
source venv/bin/activate
pip install poetry
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
poetry install

Download one of popular models to try them:

# NOTE: login in case you need to accept terms and conditions for some models
# huggingface-cli login

# gemma
huggingface-cli download second-state/Gemma-2b-it-GGUF gemma-2b-it-Q4_K_M.gguf
huggingface-cli download second-state/Gemma-7b-it-GGUF gemma-7b-it-Q4_K_M.gguf

# qwen
huggingface-cli download Qwen/Qwen1.5-0.5B-Chat-GGUF qwen1_5-0_5b-chat-q4_k_m.gguf
huggingface-cli download Qwen/Qwen1.5-1.8B-Chat-GGUF qwen1_5-1_8b-chat-q4_k_m.gguf
huggingface-cli download Qwen/Qwen1.5-4B-Chat-GGUF qwen1_5-4b-chat-q4_k_m.gguf
huggingface-cli download Qwen/Qwen1.5-7B-Chat-GGUF qwen1_5-7b-chat-q4_k_m.gguf
huggingface-cli download Qwen/Qwen1.5-14B-Chat-GGUF qwen1_5-14b-chat-q4_k_m.gguf

# mistral ai
huggingface-cli download TheBloke/dolphin-2.7-mixtral-8x7b-GGUF dolphin-2.7-mixtral-8x7b.Q3_K_M.gguf
huggingface-cli download TheBloke/dolphin-2.7-mixtral-8x7b-GGUF dolphin-2.7-mixtral-8x7b.Q4_K_M.gguf
huggingface-cli download TheBloke/dolphin-2.6-mistral-7B-GGUF dolphin-2.6-mistral-7b.Q4_K_M.gguf
huggingface-cli download second-state/MistralLite-7B-GGUF MistralLite-Q4_K_M.gguf
huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q2_K.gguf
huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q4_K_M.gguf
huggingface-cli download TheBloke/zephyr-7B-beta-GGUF zephyr-7b-beta.Q4_K_M.gguf
huggingface-cli download TheBloke/openchat-3.5-0106-GGUF openchat-3.5-0106.Q4_K_M.gguf

# stability ai
# huggingface-cli download lmz/candle-stablelm
huggingface-cli download stabilityai/stablelm-2-zephyr-1_6b stablelm-2-zephyr-1_6b-Q4_1.gguf
huggingface-cli download TheBloke/stablelm-zephyr-3b-GGUF stablelm-zephyr-3b.Q4_K_M.gguf
huggingface-cli download TheBloke/stable-code-3b-GGUF stable-code-3b.Q4_K_M.gguf

# technology innovation institute (tii)
huggingface-cli download maddes8cht/tiiuae-falcon-40b-instruct-gguf tiiuae-falcon-40b-instruct-Q3_K_M.gguf
huggingface-cli download maddes8cht/tiiuae-falcon-7b-instruct-gguf tiiuae-falcon-7b-instruct-Q4_K_M.gguf

# meta llama
huggingface-cli download TheBloke/Orca-2-7B-GGUF orca-2-7b.Q4_K_M.gguf
huggingface-cli download afrideva/MiniChat-2-3B-GGUF minichat-2-3b.q4_k_m.gguf
huggingface-cli download azarovalex/MobileLLaMA-1.4B-Chat-GGUF MobileLLaMA-1.4B-Chat-Q4_K.gguf
huggingface-cli download TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf

# microsoft phi
huggingface-cli download microsoft/phi-2
huggingface-cli download microsoft/phi-1_5
huggingface-cli download Open-Orca/oo-phi-1_5
# huggingface-cli download lmz/candle-quantized-phi
huggingface-cli download TheBloke/dolphin-2_6-phi-2-GGUF dolphin-2_6-phi-2.Q4_K_M.gguf
huggingface-cli download TheBloke/phi-2-GGUF phi-2.Q4_K_M.gguf
huggingface-cli download TKDKid1000/phi-1_5-GGUF phi-1_5-Q4_K_M.gguf

Run server:

python -B -m mli.server --llama-cpp-path='~/llama.cpp'

Run Examples

Using GPU:

NGL=99 python -B examples/sync_demo.py

Using CPU:

python -B examples/sync_demo.py
python -B examples/async_demo.py
python -B examples/langchain_sync_demo.py
python -B examples/langchain_async_demo.py

Run Production Server

Generate self-signed SSL certificates

openssl req -x509 -nodes -newkey rsa:4096 -keyout key.pem -out cert.pem -days 365

Run

python3.11 -m venv venv
source venv/bin/activate
pip install -U mlipy
python -B -m mli.server