Instructions to use 169Pi/Alpie_seed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 169Pi/Alpie_seed with Transformers:

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

pipe = pipeline("image-text-to-text", model="169Pi/Alpie_seed")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("169Pi/Alpie_seed")
model = AutoModelForMultimodalLM.from_pretrained("169Pi/Alpie_seed", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 169Pi/Alpie_seed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "169Pi/Alpie_seed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "169Pi/Alpie_seed",
		"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/169Pi/Alpie_seed

SGLang

How to use 169Pi/Alpie_seed 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 "169Pi/Alpie_seed" \
    --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": "169Pi/Alpie_seed",
		"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 "169Pi/Alpie_seed" \
        --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": "169Pi/Alpie_seed",
		"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 169Pi/Alpie_seed with Docker Model Runner:
```
docker model run hf.co/169Pi/Alpie_seed
```

deepanshupillm commited on 2 days ago

Commit

f80dbfd

verified ·

1 Parent(s): 92c7989

Update README.md

Browse files

Files changed (1) hide show

README.md +133 -75

README.md CHANGED Viewed

@@ -39,19 +39,16 @@ tags:
 <p><b>A 9B open-weight vision-language model for reasoning, coding, and multimodal understanding.</b></p>
 <p>
-<a href="https://huggingface.co/169Pi/Alpie_Seed_GGUF"><img src="https://img.shields.io/badge/📦_GGUF-2/3/4--bit-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="GGUF"></a>
 </p>
 <p>
-<a href="https://github.com/169Pi"><img src="https://img.shields.io/badge/💻_GitHub-169Pi-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="GitHub"></a>
-<a href="https://www.linkedin.com/company/169pi"><img src="https://img.shields.io/badge/💼_LinkedIn-169Pi-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="LinkedIn"></a>
-<a href="https://www.instagram.com/169pi.ai/"><img src="https://img.shields.io/badge/📸_Instagram-@169pi.ai-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="Instagram"></a>
-</p>
-<p>
-<a href="https://www.youtube.com/@169pi"><img src="https://img.shields.io/badge/▶️_YouTube-@169pi-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="YouTube"></a>
-<a href="https://x.com/169Pi_ai"><img src="https://img.shields.io/badge/𝕏_X-@169Pi__ai-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="X"></a>
-<a href="https://ollama.com/169pi"><img src="https://img.shields.io/badge/🦙_Ollama-169pi-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="Ollama"></a>
 </p>
 </div>
@@ -105,80 +102,141 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
 ## Benchmark Results
-> Alpie Seed scores are from the FP16 model and do not apply to the 2-bit, 3-bit, or 4-bit variants. Gold badge = best score in the row; purple badge = Alpie Seed score. Bold = best score in the row. Comparison-model scores are taken from published model cards and reports (including the [Qwen3.5-9B model card](https://huggingface.co/Qwen/Qwen3.5-9B)).
 ### 🧮 Language
-| | Qwen3.5-9B | Gemma 4 12B | Ministral 3 8B | GPT-OSS-20B | Sarvam-30B | Nemotron 3.5 Lightning | **Alpie Seed 9B** |
-|:---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| **Knowledge & STEM** | | | | | | | |
-| MMLU | -- | -- | -- | 85.3 | 85.1 | -- | ![87.30](https://img.shields.io/badge/87.30-F59E0B?style=flat-square) |
-| MMLU-Pro | 82.5 | 77.2 | 75.00 | 77.2 | 80.0 | 81.94 | ![82.54](https://img.shields.io/badge/82.54-F59E0B?style=flat-square) |
-| GPQA Diamond | 81.7 | 78.8 | 38.6 | 71.5 | 66.5 | 75.44 | ![84.32](https://img.shields.io/badge/84.32-F59E0B?style=flat-square) |
-| **Mathematics** | | | | | | | |
-| GSM8K | -- | -- | -- | -- | -- | -- | ![98.00](https://img.shields.io/badge/98.00-7C3AED?style=flat-square) |
-| Math-500 | -- | -- | -- | 94.2 | **97.0** | -- | ![91.00](https://img.shields.io/badge/91.00-7C3AED?style=flat-square) |
-| AIME 2026 | 69.4 | 77.5 | -- | -- | -- | -- | ![83.33](https://img.shields.io/badge/83.33-F59E0B?style=flat-square) |
-| **Coding & Software Engineering** | | | | | | | |
-| LiveCodeBench v6 | 65.6 | 72.0 | 61.6 | 61.0 | 70.0 | -- | ![72.99](https://img.shields.io/badge/72.99-F59E0B?style=flat-square) |
-| SWE-Bench Verified | 60.0 | 52.0 | -- | 60.7 | 34.0 | 51.56 | ![61.20](https://img.shields.io/badge/61.20-F59E0B?style=flat-square) |
 ### 👁️ Vision Language
-| | GPT-5-Nano-2025-08-07 | Gemini-2.5-Flash-Lite | Qwen3-VL-30B-A3B | Qwen3.5-9B | Gemma 4 12B | **Alpie Seed 9B** |
-|:---|:---:|:---:|:---:|:---:|:---:|:---:|
-| **STEM and Puzzle** | | | | | | |
-| MMMU-Pro | 57.2 | 59.7 | 63.0 | **70.1** | 69.1 | ![68.70](https://img.shields.io/badge/68.70-7C3AED?style=flat-square) |
-| MathVision | 62.2 | 52.1 | 65.7 | 78.9 | **79.7** | ![76.76](https://img.shields.io/badge/76.76-7C3AED?style=flat-square) |
-| **General VQA** | | | | | | |
-| RealWorldQA | 71.8 | 72.2 | 77.4 | 80.3 | -- | ![80.39](https://img.shields.io/badge/80.39-F59E0B?style=flat-square) |
-| MMStar | 68.6 | 69.1 | 75.5 | **79.7** | -- | ![78.87](https://img.shields.io/badge/78.87-7C3AED?style=flat-square) |
-| HallusionBench | 58.4 | 64.5 | 66.0 | 69.3 | -- | ![79.88](https://img.shields.io/badge/79.88-F59E0B?style=flat-square) |
-| **Text Recognition and Document Understanding** | | | | | | |
-| OCRBench | 75.3 | 82.5 | 83.9 | 89.2 | -- | ![90.30](https://img.shields.io/badge/90.30-F59E0B?style=flat-square) |
-* SWE-Bench Verified: resolved rate using Mini-SWE-agent, with retries disabled.
-* Comparison-model scores were not re-run by 169Pi, and harnesses, prompts, and benchmark versions differ, so cross-model comparisons are indicative rather than strictly like-for-like. Scores vary with dataset versions, prompts, evaluation harnesses, and inference settings.
-* Empty cells (--) indicate scores not yet available or not applicable.
-* MMLU for GPT-OSS-20B is from OpenAI's model card (high reasoning); MMLU for Sarvam-30B and Math-500 for Sarvam-30B and GPT-OSS-20B are from Sarvam's release comparison. Qwen3.5-9B AIME 2026 is from a third-party evaluation.
 ## Quickstart
 Serve with vLLM (OpenAI-compatible API):
 ```shell
-vllm serve 169Pi/Alpie_seed --port 8000 --max-model-len 262144 --reasoning-parser qwen3
-```
-Run locally with Ollama:
-```shell
-ollama run 169pi/alpie_seed
-```
-Quantized 2-bit, 3-bit, and 4-bit builds are in the [GGUF repository](https://huggingface.co/169Pi/Alpie_Seed_GGUF). Thinking and non-thinking behavior is controlled through the chat template.
-## Intended Use and Limitations
-Alpie Seed is intended for research, development, and general-purpose applications: reasoning, mathematics, coding, image/chart/document understanding, multilingual use, long-context analysis, and local deployments.
-- Outputs may contain factual errors, unsupported conclusions, or hallucinations.
-- Performance varies across languages, domains, and task complexity.
-- Long context does not guarantee perfect recall across the whole window.
-- Quantization may affect quality, speed, and memory differently across hardware.
-- Not a substitute for professional judgment; do not use as the sole basis for medical, legal, financial, or other high-impact decisions.
-## License
-Apache License 2.0. Users are responsible for ensuring their use and deployment comply with applicable laws and regulations.
-## Citation
-```bibtex
-@misc{alpie_seed_9b_2026,
-  title        = {Alpie Seed 9B},
-  author       = {{169Pi AI}},
-  year         = {2026},
-  howpublished = {\url{https://huggingface.co/169Pi/Alpie_seed}}
-}
-```

 <p><b>A 9B open-weight vision-language model for reasoning, coding, and multimodal understanding.</b></p>
 <p>
+  <a href="https://huggingface.co/169Pi/Alpie_Seed_GGUF"><img src="https://img.shields.io/badge/📦_GGUF-2%2F3%2F4--bit-0D9488?style=flat&labelColor=042f2e" alt="GGUF"></a>
+  <a href="https://ollama.com/169pi"><img src="https://img.shields.io/badge/🦙_Ollama-169pi-0D9488?style=flat&labelColor=042f2e" alt="Ollama"></a>
+  <a href="https://github.com/169Pi"><img src="https://img.shields.io/badge/💻_GitHub-169Pi-0D9488?style=flat&labelColor=042f2e" alt="GitHub"></a>
 </p>
 <p>
+  <a href="https://x.com/169Pi_ai"><img src="https://img.shields.io/badge/🕮_X-@169Pi__ai-0D9488?style=flat&labelColor=042f2e" alt="X"></a>
+  <a href="https://www.linkedin.com/company/169pi"><img src="https://img.shields.io/badge/💼_LinkedIn-169Pi-0D9488?style=flat&labelColor=042f2e" alt="LinkedIn"></a>
+  <a href="https://www.youtube.com/@169pi"><img src="https://img.shields.io/badge/▶️_YouTube-@169pi-0D9488?style=flat&labelColor=042f2e" alt="YouTube"></a>
+  <a href="https://www.instagram.com/169pi.ai/"><img src="https://img.shields.io/badge/📸_Instagram-@169pi.ai-0D9488?style=flat&labelColor=042f2e" alt="Instagram"></a>
 </p>
 </div>
 ## Benchmark Results
+> Alpie Seed scores are from the FP16 model and do not apply to the 2-bit, 3-bit, or 4-bit variants. **Green badge** = best score in row; **Indigo badge** = Alpie Seed score. Bold = best score among comparison models. Comparison-model scores are taken from published model cards and reports (including the [Qwen3.5-9B model card](https://huggingface.co/Qwen/Qwen3.5-9B)).
 ### 🧮 Language
+<table style="width: 100%; border-collapse: collapse; text-align: center; font-size: 14px;">
+  <thead>
+    <tr style="border-bottom: 2px solid #7C3AED; color: #7C3AED; font-weight: 600;">
+      <th style="text-align: left; padding: 10px;">Benchmark</th>
+      <th style="padding: 10px;">Qwen3.5<br>9B</th>
+      <th style="padding: 10px;">Gemma 4<br>12B</th>
+      <th style="padding: 10px;">Ministral<br>3 8B</th>
+      <th style="padding: 10px;">GPT-OSS<br>20B</th>
+      <th style="padding: 10px;">Sarvam<br>30B</th>
+      <th style="padding: 10px;">Nemotron 3.5<br>Lightning</th>
+      <th style="padding: 10px; color: #6D28D9;"><b>Alpie Seed<br>9B</b></th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr style="background-color: #F5F3FF; color: #6D28D9; font-weight: bold; text-align: left;">
+      <td colspan="8" style="padding: 8px 12px;">Knowledge &amp; STEM</td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">MMLU</td>
+      <td>--</td><td>--</td><td>--</td><td>85.3</td><td>85.1</td><td>--</td>
+      <td><img src="https://img.shields.io/badge/87.30-10B981?style=flat-square" alt="87.30"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">MMLU-Pro</td>
+      <td>82.5</td><td>77.2</td><td>75.00</td><td>77.2</td><td>80.0</td><td>81.94</td>
+      <td><img src="https://img.shields.io/badge/82.54-10B981?style=flat-square" alt="82.54"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">GPQA Diamond</td>
+      <td>81.7</td><td>78.8</td><td>38.6</td><td>71.5</td><td>66.5</td><td>75.44</td>
+      <td><img src="https://img.shields.io/badge/84.32-10B981?style=flat-square" alt="84.32"></td>
+    </tr>
+    <tr style="background-color: #F5F3FF; color: #6D28D9; font-weight: bold; text-align: left;">
+      <td colspan="8" style="padding: 8px 12px;">Mathematics</td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">GSM8K</td>
+      <td>--</td><td>--</td><td>--</td><td>--</td><td>--</td><td>--</td>
+      <td><img src="https://img.shields.io/badge/98.00-10B981?style=flat-square" alt="98.00"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">Math-500</td>
+      <td>--</td><td>--</td><td>--</td><td>94.2</td><td><b>97.0</b></td><td>--</td>
+      <td><img src="https://img.shields.io/badge/91.00-6366F1?style=flat-square" alt="91.00"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">AIME 2026</td>
+      <td>69.4</td><td>77.5</td><td>--</td><td>--</td><td>--</td><td>--</td>
+      <td><img src="https://img.shields.io/badge/83.33-10B981?style=flat-square" alt="83.33"></td>
+    </tr>
+    <tr style="background-color: #F5F3FF; color: #6D28D9; font-weight: bold; text-align: left;">
+      <td colspan="8" style="padding: 8px 12px;">Coding &amp; Software Engineering</td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">LiveCodeBench v6</td>
+      <td>65.6</td><td>72.0</td><td>61.6</td><td>61.0</td><td>70.0</td><td>--</td>
+      <td><img src="https://img.shields.io/badge/72.99-10B981?style=flat-square" alt="72.99"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">SWE-Bench Verified</td>
+      <td>60.0</td><td>52.0</td><td>--</td><td>60.7</td><td>34.0</td><td>51.56</td>
+      <td><img src="https://img.shields.io/badge/61.20-10B981?style=flat-square" alt="61.20"></td>
+    </tr>
+  </tbody>
+</table>
 ### 👁️ Vision Language
+<table style="width: 100%; border-collapse: collapse; text-align: center; font-size: 14px;">
+  <thead>
+    <tr style="border-bottom: 2px solid #7C3AED; color: #7C3AED; font-weight: 600;">
+      <th style="text-align: left; padding: 10px;">Benchmark</th>
+      <th style="padding: 10px;">GPT-5-Nano<br>2025-08-07</th>
+      <th style="padding: 10px;">Gemini-2.5<br>Flash-Lite</th>
+      <th style="padding: 10px;">Qwen3-VL<br>30B-A3B</th>
+      <th style="padding: 10px;">Qwen3.5<br>9B</th>
+      <th style="padding: 10px;">Gemma 4<br>12B</th>
+      <th style="padding: 10px; color: #6D28D9;"><b>Alpie Seed<br>9B</b></th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr style="background-color: #F5F3FF; color: #6D28D9; font-weight: bold; text-align: left;">
+      <td colspan="7" style="padding: 8px 12px;">STEM and Puzzle</td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">MMMU-Pro</td>
+      <td>57.2</td><td>59.7</td><td>63.0</td><td><b>70.1</b></td><td>69.1</td>
+      <td><img src="https://img.shields.io/badge/68.70-6366F1?style=flat-square" alt="68.70"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">MathVision</td>
+      <td>62.2</td><td>52.1</td><td>65.7</td><td>78.9</td><td><b>79.7</b></td>
+      <td><img src="https://img.shields.io/badge/76.76-6366F1?style=flat-square" alt="76.76"></td>
+    </tr>
+    <tr style="background-color: #F5F3FF; color: #6D28D9; font-weight: bold; text-align: left;">
+      <td colspan="7" style="padding: 8px 12px;">General VQA</td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">RealWorldQA</td>
+      <td>71.8</td><td>72.2</td><td>77.4</td><td>80.3</td><td>--</td>
+      <td><img src="https://img.shields.io/badge/80.39-10B981?style=flat-square" alt="80.39"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">MMStar</td>
+      <td>68.6</td><td>69.1</td><td>75.5</td><td><b>79.7</b></td><td>--</td>
+      <td><img src="https://img.shields.io/badge/78.87-6366F1?style=flat-square" alt="78.87"></td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">HallusionBench</td>
+      <td>58.4</td><td>64.5</td><td>66.0</td><td>69.3</td><td>--</td>
+      <td><img src="https://img.shields.io/badge/79.88-10B981?style=flat-square" alt="79.88"></td>
+    </tr>
+    <tr style="background-color: #F5F3FF; color: #6D28D9; font-weight: bold; text-align: left;">
+      <td colspan="7" style="padding: 8px 12px;">Text Recognition and Document Understanding</td>
+    </tr>
+    <tr style="border-bottom: 1px solid #F1F5F9;">
+      <td style="text-align: left; padding: 8px 12px;">OCRBench</td>
+      <td>75.3</td><td>82.5</td><td>83.9</td><td>89.2</td><td>--</td>
+      <td><img src="https://img.shields.io/badge/90.30-10B981?style=flat-square" alt="90.30"></td>
+    </tr>
+  </tbody>
+</table>
+- SWE-Bench Verified: resolved rate using Mini-SWE-agent, with retries disabled.
+- Comparison-model scores were not re-run by 169Pi, and harnesses, prompts, and benchmark versions differ, so cross-model comparisons are indicative rather than strictly like-for-like. Scores vary with dataset versions, prompts, evaluation harnesses, and inference settings.
+- Empty cells (--) indicate scores not yet available or not applicable.
+- MMLU for GPT-OSS-20B is from OpenAI's model card (high reasoning); MMLU for Sarvam-30B and Math-500 for Sarvam-30B and GPT-OSS-20B are from Sarvam's release comparison. Qwen3.5-9B AIME 2026 is from a third-party evaluation.
 ## Quickstart
 Serve with vLLM (OpenAI-compatible API):
 ```shell
+vllm serve 169Pi/Alpie_seed --port 8000 --max-model-len 262144 --reasoning-parser qwen3