Instructions to use QuantFactory/Violet_Twilight-v0.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Violet_Twilight-v0.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Violet_Twilight-v0.2-GGUF",
	filename="Violet_Twilight-v0.2.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use QuantFactory/Violet_Twilight-v0.2-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/Violet_Twilight-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Violet_Twilight-v0.2-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/Violet_Twilight-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Violet_Twilight-v0.2-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/Violet_Twilight-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Violet_Twilight-v0.2-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/Violet_Twilight-v0.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Violet_Twilight-v0.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Violet_Twilight-v0.2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/Violet_Twilight-v0.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/Violet_Twilight-v0.2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/Violet_Twilight-v0.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/Violet_Twilight-v0.2-GGUF:Q4_K_M

Ollama
How to use QuantFactory/Violet_Twilight-v0.2-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Violet_Twilight-v0.2-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/Violet_Twilight-v0.2-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/Violet_Twilight-v0.2-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/Violet_Twilight-v0.2-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/Violet_Twilight-v0.2-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/Violet_Twilight-v0.2-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Violet_Twilight-v0.2-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Violet_Twilight-v0.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Violet_Twilight-v0.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Violet_Twilight-v0.2-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Violet_Twilight-v0.2-GGUF

This is quantized version of Epiculous/Violet_Twilight-v0.2 created using llama.cpp

Original Model Card

Now for something a bit different, Violet_Twilight-v0.2! This model is a SLERP merge of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2!

Quants!

full / exl2 / gguf

Prompting

The v0.2 models are trained on ChatML, the prompting structure goes a little something like this:

<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant

Context and Instruct

The v0.2 models are trained on ChatML, please use that Context and Instruct template.

Current Top Sampler Settings

Spicy_Temp
Violet_Twilight-Nitral-Special

Merging

The following config was used to merge Azure Dusk and Crimson Dawn

slices:
  - sources:
      - model: Epiculous/Azure_Dusk-v0.2
        layer_range: [0, 40]
      - model: Epiculous/Crimson_Dawn-V0.2
        layer_range: [0, 40]
merge_method: slerp
base_model: Epiculous/Azure_Dusk-v0.2
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	18.53
IFEval (0-Shot)	45.32
BBH (3-Shot)	23.94
MATH Lvl 5 (4-Shot)	2.72
GPQA (0-shot)	2.13
MuSR (0-shot)	13.61
MMLU-PRO (5-shot)	23.45

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	18.53
IFEval (0-Shot)	45.32
BBH (3-Shot)	23.94
MATH Lvl 5 (4-Shot)	2.72
GPQA (0-shot)	2.13
MuSR (0-shot)	13.61
MMLU-PRO (5-shot)	23.45

Downloads last month: 116

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Datasets used to train QuantFactory/Violet_Twilight-v0.2-GGUF

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

45.320
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

23.940
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

2.720
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

2.130
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

13.610
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

23.450