Instructions to use issafuad/miqu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use issafuad/miqu with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="issafuad/miqu",
	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 issafuad/miqu with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf issafuad/miqu:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf issafuad/miqu:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf issafuad/miqu:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf issafuad/miqu: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 issafuad/miqu:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf issafuad/miqu: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 issafuad/miqu:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf issafuad/miqu:Q4_K_M

Use Docker

docker model run hf.co/issafuad/miqu:Q4_K_M

LM Studio
Jan
Ollama
How to use issafuad/miqu with Ollama:
```
ollama run hf.co/issafuad/miqu:Q4_K_M
```

Unsloth Studio new

How to use issafuad/miqu 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 issafuad/miqu 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 issafuad/miqu to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for issafuad/miqu to start chatting

Docker Model Runner
How to use issafuad/miqu with Docker Model Runner:
```
docker model run hf.co/issafuad/miqu:Q4_K_M
```

Lemonade

How to use issafuad/miqu with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull issafuad/miqu:Q4_K_M

Run and chat with the model

lemonade run user.miqu-Q4_K_M

List all available models

lemonade list

miqu 70b

First model in the potential series.

Prompt format: Mistral

<s> [INST] QUERY_1 [/INST] ANSWER_1</s> [INST] QUERY_2 [/INST] ANSWER_2</s>...

Beware that some backends (like llama.cpp) add bos already (by default), so you don't need to prepend it yourself.

Settings

DO NOT CHANGE ROPE SETTINGS. This model uses high freq base with 32k seen tokens, it should be fine for most tasks.

Only tested with temp 1 and top_p 0.95 with everything else disabled.

Downloads last month: 4

GGUF

Model size

69B params

Architecture

llama

Hardware compatibility

2-bit

4-bit

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support