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

Libraries

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

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

pipe = pipeline("text-generation", model="Auroraventures/cipher-sft-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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Auroraventures/cipher-sft-merged")
model = AutoModelForMultimodalLM.from_pretrained("Auroraventures/cipher-sft-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 Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Auroraventures/cipher-sft-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-sft-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

Unsloth Studio

How to use Auroraventures/cipher-sft-merged with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Auroraventures/cipher-sft-merged to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Auroraventures/cipher-sft-merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Auroraventures/cipher-sft-merged to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Auroraventures/cipher-sft-merged",
    max_seq_length=2048,
)

Docker Model Runner
How to use Auroraventures/cipher-sft-merged with Docker Model Runner:
```
docker model run hf.co/Auroraventures/cipher-sft-merged
```

Auroraventures commited on Apr 15

Commit

8e68484

verified ·

1 Parent(s): 81098fd

Upload cipher-simpo-train.ipynb with huggingface_hub

Browse files

Files changed (1) hide show

cipher-simpo-train.ipynb +1 -42

cipher-simpo-train.ipynb CHANGED Viewed

@@ -82,48 +82,7 @@
    "metadata": {},
    "execution_count": null,
    "outputs": [],
-   "source": [
-    "# Cell 5 — Generate SimPO preference pairs from existing SFT data\n",
-    "import json\n",
-    "from pathlib import Path\n",
-    "\n",
-    "SFT_DATA = '/content/kr8tiv-training/data/prompts/awwwards-sft.jsonl'\n",
-    "PAIRS_OUT = '/content/simpo_pairs.jsonl'\n",
-    "\n",
-    "examples = []\n",
-    "with open(SFT_DATA) as f:\n",
-    "    for line in f:\n",
-    "        if line.strip():\n",
-    "            try: examples.append(json.loads(line))\n",
-    "            except: pass\n",
-    "\n",
-    "print(f'Loaded {len(examples)} SFT examples')\n",
-    "\n",
-    "# Build preference pairs\n",
-    "pairs = []\n",
-    "skipped = 0\n",
-    "for ex in examples:\n",
-    "    msgs = ex.get('messages', [])\n",
-    "    user_msg = next((m['content'] for m in msgs if m['role']=='user'), '')\n",
-    "    chosen = next((m['content'] for m in msgs if m['role']=='assistant'), '')\n",
-    "    if not user_msg or not chosen or len(chosen) < 200:\n",
-    "        skipped += 1; continue\n",
-    "    try:\n",
-    "        rejected = generate_rejected(chosen)\n",
-    "        if not rejected or rejected == chosen or len(rejected) < 100:\n",
-    "            skipped += 1; continue\n",
-    "        pairs.append({'prompt': user_msg, 'chosen': chosen, 'rejected': rejected})\n",
-    "    except Exception as e:\n",
-    "        skipped += 1\n",
-    "\n",
-    "with open(PAIRS_OUT, 'w') as f:\n",
-    "    for p in pairs: f.write(json.dumps(p) + '\\n')\n",
-    "\n",
-    "print(f'Generated {len(pairs)} pairs, skipped {skipped}')\n",
-    "if pairs:\n",
-    "    s = pairs[0]\n",
-    "    print(f'\\nSample chosen: {len(s[\"chosen\"])} chars, rejected: {len(s[\"rejected\"])} chars')"
-   ]
   },
   {
    "cell_type": "code",

    "metadata": {},
    "execution_count": null,
    "outputs": [],
+   "source": "# Cell 5 — Generate SimPO preference pairs from existing SFT data\nimport json, traceback\nfrom pathlib import Path\n\nSFT_DATA = '/content/kr8tiv-training/data/prompts/awwwards-sft.jsonl'\nPAIRS_OUT = '/content/simpo_pairs.jsonl'\n\nexamples = []\nwith open(SFT_DATA) as f:\n    for line in f:\n        if line.strip():\n            try: examples.append(json.loads(line))\n            except: pass\n\nprint(f'Loaded {len(examples)} SFT examples')\n\n# Build preference pairs\npairs = []\nskipped = 0\nfirst_error = None\n\nfor ex in examples:\n    msgs = ex.get('messages', [])\n    user_msg = next((m['content'] for m in msgs if m['role']=='user'), '')\n    chosen = next((m['content'] for m in msgs if m['role']=='assistant'), '')\n    if not user_msg or not chosen or len(chosen) < 200:\n        skipped += 1\n        continue\n    try:\n        # Correct signature: (prompt, chosen_code)\n        rejected = generate_rejected(user_msg, chosen)\n        if not rejected or rejected == chosen or len(rejected) < 100:\n            skipped += 1\n            continue\n        pairs.append({'prompt': user_msg, 'chosen': chosen, 'rejected': rejected})\n    except Exception as e:\n        if first_error is None:\n            first_error = f'{type(e).__name__}: {e}'\n            traceback.print_exc()\n        skipped += 1\n\nwith open(PAIRS_OUT, 'w') as f:\n    for p in pairs: f.write(json.dumps(p) + '\\n')\n\nprint(f'Generated {len(pairs)} pairs, skipped {skipped}')\nif first_error:\n    print(f'First error encountered: {first_error}')\nif pairs:\n    s = pairs[0]\n    print(f'\\nSample chosen: {len(s[\"chosen\"])} chars, rejected: {len(s[\"rejected\"])} chars')\nelse:\n    raise RuntimeError('Zero pairs generated — aborting.')"
   },
   {
    "cell_type": "code",