Instructions to use Vortex5/MS3.2-24B-Solar-Skies with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vortex5/MS3.2-24B-Solar-Skies with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Vortex5/MS3.2-24B-Solar-Skies")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vortex5/MS3.2-24B-Solar-Skies")
model = AutoModelForCausalLM.from_pretrained("Vortex5/MS3.2-24B-Solar-Skies")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Vortex5/MS3.2-24B-Solar-Skies with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vortex5/MS3.2-24B-Solar-Skies"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/MS3.2-24B-Solar-Skies",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Vortex5/MS3.2-24B-Solar-Skies

SGLang

How to use Vortex5/MS3.2-24B-Solar-Skies with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Vortex5/MS3.2-24B-Solar-Skies" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/MS3.2-24B-Solar-Skies",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Vortex5/MS3.2-24B-Solar-Skies" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/MS3.2-24B-Solar-Skies",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Vortex5/MS3.2-24B-Solar-Skies with Docker Model Runner:
```
docker model run hf.co/Vortex5/MS3.2-24B-Solar-Skies
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🔥 MS3.2-24B-Solar-Skies

Bright minds under boundless skies — where every conversation becomes a sunrise of imagination

🧬 Overview

MS3.2-24B-Solar-Skies merge of pre-trained language models created using MergeKit.
It draws upon the intellectual density of The Omega Directive, the expressive prose of Fiery Lynx, and the measured balance of Chaos Skies.

⚙️ Merge Method — Multi-SLERP

🧩 Models:

🧠 ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0
🔥 Vortex5/MS3.2-24B-Fiery-Lynx
🌌 Vortex5/MS3.2-24B-Chaos-Skies

Configuration

models:
  - model: ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0
    parameters:
      weight:
        - filter: self_attn
          value: [0.20, 0.35, 0.55, 0.75, 1.00, 0.95, 0.80, 0.50]
        - filter: norm
          value: 0.45
        - value: 0.33
  - model: Vortex5/MS3.2-24B-Fiery-Lynx
    parameters:
      weight:
      - filter: lm_head
        value: 0.34
      - filter: mlp
        value: [0.20, 0.30, 0.45, 0.60, 0.65, 0.60, 0.45, 0.30]
      - value: 0.25
  - model: Vortex5/MS3.2-24B-Chaos-Skies
    parameters:
      weight:
      - filter: self_attn
        value: [0.25, 0.35, 0.45, 0.55, 0.60, 0.65, 0.65, 0.60]
      - filter: mlp
        value: 0.2
      - value: 0.33
merge_method: multislerp
dtype: bfloat16
parameters:
  normalize: true
tokenizer:
  source: Vortex5/MS3.2-24B-Chaos-Skies

🎭 Intended Use

Category	Description
🧘 Reflective Dialogue	Ideal for introspective or philosophical discussions, exploring abstract and emotional topics.
🖋️ Creative Writing	Excels at expressive prose, narrative storytelling, and immersive worldbuilding.
🧠 Analytical Reasoning	Balances logic and creativity for insightful, stylistically nuanced explanations.
💞 Character Roleplay	Adapts fluidly to emotional, character-driven interactions and narrative depth.

🌒 Acknowledgements

⚙️ mradermacher — static / imatrix quantization
🜛 DeathGodlike — EXL3 quants
💫 All original model authors and contributors whose work formed the foundation for this merge.

Downloads last month: 5

Safetensors

Model size

24B params

Tensor type

BF16

Model tree for Vortex5/MS3.2-24B-Solar-Skies

ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0

Vortex5/MS3.2-24B-Chaos-Skies

Vortex5/MS3.2-24B-Fiery-Lynx

Merge model

this model

Quantizations

4 models