Instructions to use DarkArtsForge/Helix-SCE-12B-jh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DarkArtsForge/Helix-SCE-12B-jh with Transformers:

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

pipe = pipeline("text-generation", model="DarkArtsForge/Helix-SCE-12B-jh")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DarkArtsForge/Helix-SCE-12B-jh")
model = AutoModelForCausalLM.from_pretrained("DarkArtsForge/Helix-SCE-12B-jh")
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 Settings

vLLM

How to use DarkArtsForge/Helix-SCE-12B-jh with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DarkArtsForge/Helix-SCE-12B-jh"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DarkArtsForge/Helix-SCE-12B-jh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DarkArtsForge/Helix-SCE-12B-jh

SGLang

How to use DarkArtsForge/Helix-SCE-12B-jh 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 "DarkArtsForge/Helix-SCE-12B-jh" \
    --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": "DarkArtsForge/Helix-SCE-12B-jh",
		"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 "DarkArtsForge/Helix-SCE-12B-jh" \
        --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": "DarkArtsForge/Helix-SCE-12B-jh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

🧬 Helix SCE 12B jh

retokenized chatml version of DarkArtsForge/Helix-SCE-12B

this was created using the command C:\mergekit-new>mergekit-tokensurgeon "B:\12B\HelixA-12B" "B:\12B\Vortex5--Prototype-X-12b" Helix-SCE-12B-jh --approximation-method john_hewitt

possibly smarter than the regular tekken version, testing is in progress

only a couple errors reported

note: safetensors are NOT identical, you will need to redownload all files to quantize

WARNING:root:This script is experimental and may produce unexpected results.
WARNING:mergekit.tokenizer.normalization:Unknown tokenizer type - assuming 'Ġ' word start prefix
WARNING:mergekit.tokenizer.normalization:Unknown tokenizer type - assuming 'Ġ' word start prefix
Approximating tokens: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:12<00:00, 12.33s/it]
Approximating tokens: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:12<00:00, 12.20s/it]
Saving weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 363/363 [00:34<00:00, 10.41it/s]

Downloads last month: 87

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for DarkArtsForge/Helix-SCE-12B-jh

Base model

DarkArtsForge/Helix-SCE-12B

Finetuned

(2)

this model

Quantizations

2 models