Instructions to use Auroraventures/cipher-sft25-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Auroraventures/cipher-sft25-merged with Transformers:

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

pipe = pipeline("text-generation", model="Auroraventures/cipher-sft25-merged")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Auroraventures/cipher-sft25-merged")
model = AutoModelForImageTextToText.from_pretrained("Auroraventures/cipher-sft25-merged")
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

vLLM

How to use Auroraventures/cipher-sft25-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Auroraventures/cipher-sft25-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Auroraventures/cipher-sft25-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Auroraventures/cipher-sft25-merged

SGLang

How to use Auroraventures/cipher-sft25-merged 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 "Auroraventures/cipher-sft25-merged" \
    --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": "Auroraventures/cipher-sft25-merged",
		"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 "Auroraventures/cipher-sft25-merged" \
        --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": "Auroraventures/cipher-sft25-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Auroraventures/cipher-sft25-merged with Docker Model Runner:
```
docker model run hf.co/Auroraventures/cipher-sft25-merged
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Cipher SFT 2.5 — Synthetic (v2, retired) 🦑⚠️

Superseded by cipher-sft25-real-merged. Archived for reproducibility.

This is the v2 Awwwards SFT checkpoint of the Cipher series, trained on a synthetic dataset of 288 Awwwards-style triples distilled from a larger instruction-tuned model.

During evaluation the model suffered template collapse: many generations rolled back to the same 5-section landing template regardless of prompt. This is why a v3 pass on real, scraped source code (cipher-sft25-real-merged) was launched and is now the recommended checkpoint.

🧠 Base: Auroraventures/cipher-simpo-merged
📚 Dataset: awwwards-stage25-sft.jsonl (288 synthetic records, 1.9 MB)
⚠️ Status: Retired — use v3 instead for production
📦 GGUF: cipher-sft25-merged-Q4_K_M-GGUF

Why retired?

Synthetic SFT that distills from another LM converges on the teacher's mean aesthetic — very few outlier designs — and under-weights the long tail that makes Awwwards sites Awwwards sites. Symptoms:

Identical hero layouts across divergent prompts
Repeated color tokens (#9bf, #a4f) regardless of brief
Repeated section ordering: hero → about → services → work → contact

The fix was real data: 578 Three.js examples, 148 Motion dev files, 63 GSAP gallery snippets, ≤998 aura shells → shipped as the cipher-real-v1-sft.jsonl (5.66 MB) dataset split.

License

CC-BY-NC-4.0. Gemma-4 terms apply.

Built with 🦑 by Aurora Ventures.

Downloads last month: 6

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for Auroraventures/cipher-sft25-merged

Base model

Auroraventures/cipher-sft-merged

Finetuned

Auroraventures/cipher-simpo-merged

Finetuned

(1)

this model

Quantizations

1 model

Auroraventures
/

cipher-sft25-merged

Cipher SFT 2.5 — Synthetic (v2, retired) 🦑⚠️

Why retired?

License

Model tree for Auroraventures/cipher-sft25-merged

Dataset used to train Auroraventures/cipher-sft25-merged