Not-For-All-Audiences

Instructions to use QuantFactory/L3.1-8B-komorebi-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/L3.1-8B-komorebi-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/L3.1-8B-komorebi-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/L3.1-8B-komorebi-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/L3.1-8B-komorebi-GGUF",
	filename="L3.1-8B-komorebi.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use QuantFactory/L3.1-8B-komorebi-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/L3.1-8B-komorebi-GGUF: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 QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/L3.1-8B-komorebi-GGUF: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 QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/L3.1-8B-komorebi-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/L3.1-8B-komorebi-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 QuantFactory/L3.1-8B-komorebi-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 QuantFactory/L3.1-8B-komorebi-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/L3.1-8B-komorebi-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use QuantFactory/L3.1-8B-komorebi-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/L3.1-8B-komorebi-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/L3.1-8B-komorebi-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.L3.1-8B-komorebi-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/L3.1-8B-komorebi-GGUF

This is quantized version of crestf411/L3.1-8B-komorebi created using llama.cpp

Original Model Card

This is a model based on a multi-phase process using KTO fine tuning using the jondurbin gutenberg approach, that results in 3 separate LoRAs which are merged in sequence.

The resulting model is exhibiting a significant decrease in Llama 3.1 slop outputs.

Experimental. Please give feedback. Begone if you demand perfection.

I did most of my testing with temp 1.4, min-p 0.15, DRY 0.8. I also did play with enabling XTC with threshold 0.1, prob 0.50.

As context grows, you may want to bump temp and min-p and maybe even DRY.

Downloads last month: 31

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Paper for QuantFactory/L3.1-8B-komorebi-GGUF

KTO: Model Alignment as Prospect Theoretic Optimization

Paper • 2402.01306 • Published Feb 2, 2024 • 22