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

Libraries

How to use Vortex5/MS3.2-24B-Fiery-Lynx with Transformers:

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

pipe = pipeline("text-generation", model="Vortex5/MS3.2-24B-Fiery-Lynx")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vortex5/MS3.2-24B-Fiery-Lynx")
model = AutoModelForCausalLM.from_pretrained("Vortex5/MS3.2-24B-Fiery-Lynx")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Vortex5/MS3.2-24B-Fiery-Lynx 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-Fiery-Lynx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/MS3.2-24B-Fiery-Lynx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vortex5/MS3.2-24B-Fiery-Lynx

SGLang

How to use Vortex5/MS3.2-24B-Fiery-Lynx 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-Fiery-Lynx" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/MS3.2-24B-Fiery-Lynx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-Fiery-Lynx" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/MS3.2-24B-Fiery-Lynx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

MS3.2-24B-Fiery-Lynx

Instruct template: Mistral V7

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using ConicCat/Mistral-Small-3.2-AntiRep-24B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: zerofata/MS3.2-PaintedFantasy-v2-24B
    parameters:
      weight: 0.2
      density: 0.5
      epsilon: 0.4
  - model: Gryphe/Codex-24B-Small-3.2
    parameters:
      weight: 0.2 
      density: 0.5
      epsilon: 0.4
  - model: CrucibleLab/M3.2-24B-Loki-V1.3
    parameters:
      weight: 0.4
      density: 0.4
      epsilon: 0.3
merge_method: della_linear
base_model: ConicCat/Mistral-Small-3.2-AntiRep-24B
parameters:
  lambda: 0.9
  normalize: true
dtype: bfloat16
tokenizer:
 source: union