Instructions to use miqudev/miqu-1-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use miqudev/miqu-1-70b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="miqudev/miqu-1-70b", filename="miqu-1-70b.q2_K.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use miqudev/miqu-1-70b with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf miqudev/miqu-1-70b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf miqudev/miqu-1-70b:Q4_K_M
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 miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf miqudev/miqu-1-70b:Q4_K_M
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 miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf miqudev/miqu-1-70b:Q4_K_M
Use Docker
docker model run hf.co/miqudev/miqu-1-70b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use miqudev/miqu-1-70b with Ollama:
ollama run hf.co/miqudev/miqu-1-70b:Q4_K_M
- Unsloth Studio new
How to use miqudev/miqu-1-70b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for miqudev/miqu-1-70b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for miqudev/miqu-1-70b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for miqudev/miqu-1-70b to start chatting
- Docker Model Runner
How to use miqudev/miqu-1-70b with Docker Model Runner:
docker model run hf.co/miqudev/miqu-1-70b:Q4_K_M
- Lemonade
How to use miqudev/miqu-1-70b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull miqudev/miqu-1-70b:Q4_K_M
Run and chat with the model
lemonade run user.miqu-1-70b-Q4_K_M
List all available models
lemonade list
Full precision weights
Are there full precision weights without quantization?
/ /(。•‿•。)\ \۶🥬 yeee
miqu -> mi qu -> mistral quantized
It's quantized by design™ (or for leak purposes, depending on how you look at it).
@imone , you are a little late to the party. there was a whole 24-hour long discussion that was closed by the creator of this repo. please check that out.
Just read through the whole thing. It's crazy how unorganized it got that HF staff had to get involved and lock it
miqu -> mi qu -> mistral quantized
It's quantized by design™ (or for leak purposes, depending on how you look at it).
It refers to me uploading q2k only, it gained more traction than I anticipated and I folded and uploaded bigger ones.