Instructions to use Naphula-Archives/Piranha-12B-v1a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula-Archives/Piranha-12B-v1a with Transformers:

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

pipe = pipeline("text-generation", model="Naphula-Archives/Piranha-12B-v1a")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula-Archives/Piranha-12B-v1a")
model = AutoModelForCausalLM.from_pretrained("Naphula-Archives/Piranha-12B-v1a", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

NeMo
How to use Naphula-Archives/Piranha-12B-v1a with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Naphula-Archives/Piranha-12B-v1a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula-Archives/Piranha-12B-v1a"
# 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-Archives/Piranha-12B-v1a",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula-Archives/Piranha-12B-v1a

SGLang

How to use Naphula-Archives/Piranha-12B-v1a 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-Archives/Piranha-12B-v1a" \
    --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-Archives/Piranha-12B-v1a",
		"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-Archives/Piranha-12B-v1a" \
        --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-Archives/Piranha-12B-v1a",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula-Archives/Piranha-12B-v1a with Docker Model Runner:
```
docker model run hf.co/Naphula-Archives/Piranha-12B-v1a
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🐟 Piranha 12B v1a

A prototype test for Savage Sands. This one is partially censored (despite having all uncensored components) but very creative. Therefore, the merge is "failed" because it should not have refusals. It was good enough to upload however. It recommended a "Piranha Tank", hence the name.

I tested with unablated base_model, and it seems this increased refusals a bit more.

architecture: MistralForCausalLM
base_model: B:/12B/MuXodious--Mistral-Nemo-Instruct-2407-absolute-heresy # mistralai--Mistral-Nemo-Instruct-2407
models:
  - model: B:/12B/EldritchLabs--MN-12B-RP-Ink-Longform-MPOA
    parameters:
      weight: 1.0
  - model: B:/12B/EldritchLabs--Human-Like-Mistral-Nemo-Instruct-2407-MPOA
    parameters:
      weight: 1.0
  - model: B:/12B/MuXodious-Rocinante-X-12B-v1-absolute-heresy # TheDrummer--Rocinante-X-12B-v1
    parameters:
      weight: 1.0
merge_method: karcher_stock # v12B
parameters:  
  filter_wise: true
  max_iter: 25
  min_iter: 10
  tol: 1.0e-9
  magnitude_mean_geometric: false # TRUE makes it 75% karcher
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto
name: karcher_stock_12b_v1

Downloads last month: 26

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for Naphula-Archives/Piranha-12B-v1a

EldritchLabs/Human-Like-Mistral-Nemo-Instruct-2407-MPOA

EldritchLabs/MN-12B-RP-Ink-Longform-MPOA

MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy

MuXodious/Rocinante-X-12B-v1-absolute-heresy

Merge model

this model

Quantizations

3 models