Instructions to use liminerity/M7-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liminerity/M7-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="liminerity/M7-7b-GGUF",
	filename="multiverse-experiment-slerp-7b.Q5_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use liminerity/M7-7b-GGUF 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 liminerity/M7-7b-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf liminerity/M7-7b-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf liminerity/M7-7b-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf liminerity/M7-7b-GGUF:Q5_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 liminerity/M7-7b-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf liminerity/M7-7b-GGUF:Q5_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 liminerity/M7-7b-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf liminerity/M7-7b-GGUF:Q5_K_M

Use Docker

docker model run hf.co/liminerity/M7-7b-GGUF:Q5_K_M

LM Studio
Jan
Ollama
How to use liminerity/M7-7b-GGUF with Ollama:
```
ollama run hf.co/liminerity/M7-7b-GGUF:Q5_K_M
```

Unsloth Studio

How to use liminerity/M7-7b-GGUF 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 liminerity/M7-7b-GGUF 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 liminerity/M7-7b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for liminerity/M7-7b-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use liminerity/M7-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/liminerity/M7-7b-GGUF:Q5_K_M
```

Lemonade

How to use liminerity/M7-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull liminerity/M7-7b-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.M7-7b-GGUF-Q5_K_M

List all available models

lemonade list

Is it censored?

by supercharge19 - opened Mar 13, 2024

Discussion

supercharge19

Mar 13, 2024

Is the model helpful or censored?

gate369

liminerity org Mar 13, 2024

Quantized is alright it’s got a bug where it’ll say “instinstinst” but it seems alright for the most part. More than likely needs to be fine tuned but I’m extremely limited with what I can do atm

supercharge19

Mar 14, 2024

Bug in the model itself or in quantized verion (how can bug creep into quantization if not present in original?)?

It is no fun, you can't even make a plan to rob a bank :( or legalize bank robbing. :P

gate369

liminerity org Mar 15, 2024

@supercharge19 i have only tryed q5_k quantized. i dont have the computing power to run models like that. the bug came from merging 2 different models together. It has to be finetuned to Iron this out

supercharge19

Mar 16, 2024

what suitable (smallest) opensource dataset to use to "iron this out"?

gate369

liminerity org Mar 17, 2024

@supercharge19 to be honest man idk im self taught and trying to learn still. Im really just a autistic dude

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

Tap or paste here to upload images

· Sign up or log in to comment