Instructions to use starble-dev/Starlight-V3-12B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use starble-dev/Starlight-V3-12B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("starble-dev/Starlight-V3-12B-GGUF", dtype="auto")

llama-cpp-python

How to use starble-dev/Starlight-V3-12B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="starble-dev/Starlight-V3-12B-GGUF",
	filename="Starlight-V3-12B-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 starble-dev/Starlight-V3-12B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf starble-dev/Starlight-V3-12B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf starble-dev/Starlight-V3-12B-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 starble-dev/Starlight-V3-12B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf starble-dev/Starlight-V3-12B-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 starble-dev/Starlight-V3-12B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf starble-dev/Starlight-V3-12B-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 starble-dev/Starlight-V3-12B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf starble-dev/Starlight-V3-12B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/starble-dev/Starlight-V3-12B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use starble-dev/Starlight-V3-12B-GGUF with Ollama:
```
ollama run hf.co/starble-dev/Starlight-V3-12B-GGUF:Q4_K_M
```

Unsloth Studio

How to use starble-dev/Starlight-V3-12B-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 starble-dev/Starlight-V3-12B-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 starble-dev/Starlight-V3-12B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for starble-dev/Starlight-V3-12B-GGUF to start chatting

Docker Model Runner
How to use starble-dev/Starlight-V3-12B-GGUF with Docker Model Runner:
```
docker model run hf.co/starble-dev/Starlight-V3-12B-GGUF:Q4_K_M
```

Lemonade

How to use starble-dev/Starlight-V3-12B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull starble-dev/Starlight-V3-12B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Starlight-V3-12B-GGUF-Q4_K_M

List all available models

lemonade list

General Use Sampling:
Mistral-Nemo-12B is very sensitive to the temperature sampler, try values near 0.3 at first or else you will get some weird results. This is mentioned by MistralAI at their Transformers section.

Best Samplers:
I found best success using the following for Starlight-V3-12B:
Temperature: 0.7-1.2 (Additional stopping strings will be necessary as you increase the temperature)
Top K: -1
Min P: 0.05
Rep Penalty: 1.03-1.1

Why Version 3?

Currently the other versions resulted in really bad results that I didn't upload them, the version number is just the internal version.

Goal

The idea is to keep the strengths of anthracite-org/magnum-12b-v2 while adding some more creativity that seems to be lacking in the model. Mistral-Nemo by itself seems to behave less sporadic due to the low temperature needed but this gets a bit repetitive, although it's still the best foundational model I've used so far, mainly since Mistral-Nemo native 128k context length is crazy good.

Results

I am not entirely pleased with the result of the merge but it seems okay, though base anthracite-org/magnum-12b-v2 might just be better by itself. However, I'll still experiement on different merge methods. Leaking of the training data used on both models seems a bit more apparent when using higher temperature values, especially the use of author notes on the system prompt. Generally I'd advise to create a stopping string for "```" to avoid the generation of the training data.

Original Models:

UsernameJustAnother/Nemo-12B-Marlin-v5 (Thank you so much for your work ♥)
anthracite-org/magnum-12b-v2 (Thank you so much for your work ♥)

Official Quants: PPL = Perplexity, lower is better
Comparisons are done as QX_X Llama-3-8B against FP16 Llama-3-8B, recommended as a guideline and not as fact.

Quant Type	Note	Size
Q2_K	+3.5199 ppl @ Llama-3-8B	4.79 GB
Q3_K_S	+1.6321 ppl @ Llama-3-8B	5.53 GB
Q3_K_M	+0.6569 ppl @ Llama-3-8B	6.08 GB
Q3_K_L	+0.5562 ppl @ Llama-3-8B	6.56 GB
Q4_K_S	+0.2689 ppl @ Llama-3-8B	7.12 GB
Q4_K_M	+0.1754 ppl @ Llama-3-8B	7.48 GB
Q5_K_S	+0.1049 ppl @ Llama-3-8B	8.52 GB
Q5_K_M	+0.0569 ppl @ Llama-3-8B	8.73 GB
Q6_K	+0.0217 ppl @ Llama-3-8B	10.1 GB
Q8_0	+0.0026 ppl @ Llama-3-8B	13.00 GB

Original Model Licenses & This Model License: Apache 2.0

Downloads last month: 72

GGUF

Model size

12B 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

Model tree for starble-dev/Starlight-V3-12B-GGUF

Base model

starble-dev/Starlight-V3-12B

Quantized

(3)

this model