Instructions to use Naphula/StationV-24B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/StationV-24B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Naphula/StationV-24B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/StationV-24B-v1")
model = AutoModelForCausalLM.from_pretrained("Naphula/StationV-24B-v1")
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 Naphula/StationV-24B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/StationV-24B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/StationV-24B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/StationV-24B-v1

SGLang

How to use Naphula/StationV-24B-v1 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 "Naphula/StationV-24B-v1" \
    --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": "Naphula/StationV-24B-v1",
		"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 "Naphula/StationV-24B-v1" \
        --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": "Naphula/StationV-24B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/StationV-24B-v1 with Docker Model Runner:
```
docker model run hf.co/Naphula/StationV-24B-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

⚠️ Warning: This merge is partially broken due to using 2501 and 2503 finetunes, it may have weak prompt adherence.

Station V

Goetia checkpoint test, a modified expansion of the Circuitry/Rotor series.

models:
  - model: Delta-Vector/Rei-24B-KTO
    parameters:
      density: 0.5
      weight: 0.1
  - model: TheDrummer/Magidonia-24B-v4.2.0
    parameters:
      density: 0.6
      weight: 0.12
  - model: zerofata/MS3.2-PaintedFantasy-v3-24B
    parameters:
      density: 0.6
      weight: 0.12
  - model: ReadyArt/Broken-Tutu-24B-Transgression-v2.0
    parameters:
      density: 0.6
      weight: 0.12
  - model: LatitudeGames/Hearthfire-24B
    parameters:
      density: 0.6
      weight: 0.12
  - model: CrucibleLab/M3.2-24B-Loki-V1.3
    parameters:
      density: 0.5
      weight: 0.1
  - model: SicariusSicariiStuff/Impish_Magic_24B
    parameters:
      density: 0.5
      weight: 0.1
  - model: aixonlab/Eurydice-24b-v3.5
    parameters:
      density: 0.5
      weight: 0.1
  - model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
    parameters:
      density: 0.5
      weight: 0.1
  - model: Darkhn/M3.2-24B-Animus-V7.1
    parameters:
      density: 0.5
      weight: 0.1
  - model: Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
    parameters:
      density: 0.6
      weight: 0.12
  - model: trashpanda-org/MS3.2-24B-Mullein-v2
    parameters:
      density: 0.5
      weight: 0.1
  - model: Doctor-Shotgun/MS3.2-24B-Magnum-Diamond
    parameters:
      density: 0.5
      weight: 0.1
  - model: Undi95/MistralThinker-v1.1
    parameters:
      density: 0.5
      weight: 0.1
base_model: TheDrummer/Precog-24B-v1
merge_method: ties
parameters:
  normalize: false
  int8_mask: false
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto
name: StationV-24B-v1