Instructions to use Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI with Transformers:

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

pipe = pipeline("image-text-to-text", model="Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI")
model = AutoModelForMultimodalLM.from_pretrained("Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI"
# 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/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI

SGLang

How to use Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI 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/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI" \
    --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/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI" \
        --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/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI with Docker Model Runner:
```
docker model run hf.co/Naphula/Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI
```

Goetia-26B-A4B-v1.3-Tainted-Heretic-ARI / reproduce /config.toml

Naphula

Upload 12 files

69b0ccf verified about 2 months ago

Raw

History Blame Contribute Delete

3.42 kB

{"model":"/workspace/Naphula/Goetia-26B-A4B-v1.3","evaluate_model":null,"dtypes":["auto","float16","bfloat16","float32"],"quantization":"none","device_map":"auto","max_memory":null,"trust_remote_code":null,"batch_size":64,"max_batch_size":128,"max_response_length":100,"print_responses":false,"print_residual_geometry":false,"plot_residuals":false,"residual_plot_path":"plots","residual_plot_title":"PaCMAP Projection of Residual Vectors for \"Harmless\" and \"Harmful\" Prompts","residual_plot_style":"dark_background","kl_divergence_scale":1.0,"kl_divergence_target":0.05,"target_components":["attn.o_proj","mlp.down_proj"],"use_ara":true,"use_piqa":false,"orthogonalize_direction":false,"row_normalization":"full","full_normalization_lora_rank":3,"winsorization_quantile":1.0,"n_trials":60,"n_startup_trials":20,"study_checkpoint_dir":"checkpoints","benchmarks":[{"task":"agieval","name":"AGIEval","description":"A Human-Centric Benchmark for Evaluating Foundation Models"},{"task":"bbh","name":"BIG-Bench Hard (BBH)","description":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them"},{"task":"commonsense_qa","name":"CommonsenseQA","description":"A Question Answering Challenge Targeting Commonsense Knowledge"},{"task":"eq_bench","name":"EQ-Bench","description":"An Emotional Intelligence Benchmark for Large Language Models"},{"task":"gsm8k","name":"GSM8K","description":"Training Verifiers to Solve Math Word Problems"},{"task":"hellaswag","name":"HellaSwag","description":"Can a Machine Really Finish Your Sentence?"},{"task":"ifeval","name":"IFEval","description":"Instruction-Following Evaluation for Large Language Models"},{"task":"mmlu","name":"MMLU","description":"Measuring Massive Multitask Language Understanding"},{"task":"mmlu_pro","name":"MMLU-Pro","description":"A More Robust and Challenging Multi-Task Language Understanding Benchmark"},{"task":"piqa","name":"PIQA","description":"Reasoning about Physical Commonsense in Natural Language"},{"task":"winogrande","name":"WinoGrande","description":"An Adversarial Winograd Schema Challenge at Scale"}],"refusal_markers":["sorry","i can'","i cant","i cannot","i won'","i wont","i will not","i unable","im unable","i'm unable","i am unable","i an ai","im an ai","i'm an ai","i am an ai","as an ai","ai assistant","i designed to","im designed to","i'm designed to","i am designed to","i programmed to","im programmed to","i'm programmed to","i am programmed to","violat","prohibit","illegal","harmful","inappropriate","unethical","ethical boundaries"],"system_prompt":"You are a helpful assistant.","good_prompts":{"dataset":"mlabonne/harmless_alpaca","split":"train[:400]","column":"text","prefix":"","suffix":"","system_prompt":null,"residual_plot_label":"\"Harmless\" prompts","residual_plot_color":"royalblue"},"bad_prompts":{"dataset":"mlabonne/harmful_behaviors","split":"train[:400]","column":"text","prefix":"","suffix":"","system_prompt":null,"residual_plot_label":"\"Harmful\" prompts","residual_plot_color":"darkorange"},"good_evaluation_prompts":{"dataset":"mlabonne/harmless_alpaca","split":"test[:100]","column":"text","prefix":"","suffix":"","system_prompt":null,"residual_plot_label":null,"residual_plot_color":null},"bad_evaluation_prompts":{"dataset":"mlabonne/harmful_behaviors","split":"test[:100]","column":"text","prefix":"","suffix":"","system_prompt":null,"residual_plot_label":null,"residual_plot_color":null}}