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 1 day ago

Commit

f0d79e8

verified ·

1 Parent(s): 7eed28a

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -15

README.md CHANGED Viewed

@@ -106,7 +106,7 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
 >
 > Alpie Seed scores are from the FP16 model and do not apply to the 2-bit, 3-bit, or 4-bit variants. **Bold** indicates the best score in each 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
 <table style="width: 100%; border-collapse: collapse; text-align: center; font-size: 14px;">
   <thead>
@@ -127,7 +127,7 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
     </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><b>87.30</b></td>
     </tr>
     <tr style="border-bottom: 1px solid #F1F5F9;">
@@ -143,16 +143,6 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
     <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><b>98.00</b></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>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>
@@ -174,7 +164,7 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
   </tbody>
 </table>
-### Vision Language
 <table style="width: 100%; border-collapse: collapse; text-align: center; font-size: 14px;">
   <thead>
@@ -234,13 +224,15 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
 - 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
 ### Install dependencies
-Alpie Seed support requires a recent Transformers release (Transformers 5 or later).
 ```bash
 pip install -U "transformers>=5.2.0" torch torchvision pillow accelerate

 >
 > Alpie Seed scores are from the FP16 model and do not apply to the 2-bit, 3-bit, or 4-bit variants. **Bold** indicates the best score in each 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
 <table style="width: 100%; border-collapse: collapse; text-align: center; font-size: 14px;">
   <thead>
     </tr>
     <tr style="border-bottom: 1px solid #F1F5F9;">
       <td style="text-align: left; padding: 8px 12px;">MMLU</td>
+      <td>--</td><td>--</td><td>76.1*</td><td>85.3</td><td>85.1</td><td>78.63*</td>
       <td><b>87.30</b></td>
     </tr>
     <tr style="border-bottom: 1px solid #F1F5F9;">
     <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;">AIME 2026</td>
       <td>69.4</td><td>77.5</td><td>--</td><td>--</td><td>--</td><td>--</td>
   </tbody>
 </table>
+### 👁️ Vision Language
 <table style="width: 100%; border-collapse: collapse; text-align: center; font-size: 14px;">
   <thead>
 - 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 is from Sarvam's release comparison. Ministral 3 8B (76.1) is the published 5-shot MMLU score for its base checkpoint, and Nemotron 3.5 Lightning (78.63) is the published base-model exact-match score. These settings/checkpoints are not strictly like-for-like with every other entry. Qwen3.5-9B and Gemma 4 12B are shown as -- because their cited model cards report MMLU-Pro / MMLU-Redux rather than the same standard MMLU result; those metrics should not be substituted into the MMLU row.
+- AIME 2026 entries are shown only where a score for that exact benchmark is available in the cited material. AIME 2025 results are not substituted for AIME 2026. Qwen3.5-9B AIME 2026 is from a third-party evaluation.
+- Sources: [Ministral 3 8B model card](https://www.modelscope.cn/models/mistralai/Ministral-3-8B-Instruct-2512-BF16), [NVIDIA Nemotron 3.5 Lightning evaluation](https://docs.nvidia.com/nemotron/nightly/nemotron/lightning35/evaluate.html), [Qwen3.5-9B model card](https://huggingface.co/Qwen/Qwen3.5-9B), [Gemma 4 model card](https://huggingface.co/google/gemma-4-12B), [GPT-OSS evaluation](https://deploymentsafety.openai.com/gpt-oss), and [Sarvam-30B model card](https://huggingface.co/sarvamai/sarvam-30b).
 ## Quickstart
 ### Install dependencies
+Qwen3.5 support requires a recent Transformers release (Transformers 5 or later).
 ```bash
 pip install -U "transformers>=5.2.0" torch torchvision pillow accelerate