Instructions to use Infomaniak-AI/Apertus-1.5-70B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Infomaniak-AI/Apertus-1.5-70B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="Infomaniak-AI/Apertus-1.5-70B-Instruct")
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 AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("Infomaniak-AI/Apertus-1.5-70B-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Infomaniak-AI/Apertus-1.5-70B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Infomaniak-AI/Apertus-1.5-70B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infomaniak-AI/Apertus-1.5-70B-Instruct",
		"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/Infomaniak-AI/Apertus-1.5-70B-Instruct

SGLang

How to use Infomaniak-AI/Apertus-1.5-70B-Instruct 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 "Infomaniak-AI/Apertus-1.5-70B-Instruct" \
    --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": "Infomaniak-AI/Apertus-1.5-70B-Instruct",
		"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 "Infomaniak-AI/Apertus-1.5-70B-Instruct" \
        --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": "Infomaniak-AI/Apertus-1.5-70B-Instruct",
		"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 Infomaniak-AI/Apertus-1.5-70B-Instruct with Docker Model Runner:
```
docker model run hf.co/Infomaniak-AI/Apertus-1.5-70B-Instruct
```

Alvor

aryan-ahadinia commited on Jul 24

Commit

aeba489

1 Parent(s): dd0b87b

[gh-mirror] Sync `apertus_1.5` from GitHub PR #10 (#3)

Browse files

- [gh-mirror] Sync `apertus_1.5` from GitHub PR #10 (7d792912b311e7bd025a945653ef2aad995b55e4)

Co-authored-by: Aryan Ahadinia <aryan-ahadinia@users.noreply.huggingface.co>

Files changed (2) hide show

README.md +1 -1
assets/visual_performance_plot.png +2 -2

README.md CHANGED Viewed

@@ -300,7 +300,7 @@ Text benchmarks cover various domains like knowledge (MMLU, MMLU-Pro, AGIEval, A
 ![Visual Performance](https://raw.githubusercontent.com/swiss-ai/model-cards-assets/main/apertus_1.5/visual_performance_plot.png)
-Image benchmarks cover general VQA and perception (GQA, MMStar, RealWorldQA, VQAv2), robustness and bias (MMVP, VLMs-Are-Biased, VLMsAreBlind), documents and OCR (ChartQA, DocVQA, SEED-Bench-2-Plus), visual math and logic (BabyVision, MathVision), STEM knowledge (AI2D, MMMU), remote sensing (FRIEDA, GeoBench, VRSBench, VRSBench-VQA), hallucination alignment (POPE), and medical imaging (PathVQA, PMC-VQA, SLAKE, VQA-RAD).
 ## Training

 ![Visual Performance](https://raw.githubusercontent.com/swiss-ai/model-cards-assets/main/apertus_1.5/visual_performance_plot.png)
+Image benchmarks cover general VQA and perception (GQA, MMStar, RealWorldQA, VQAv2, V\*Bench, CountBench), robustness and bias (MMVP, VLMs-Are-Biased, VLMsAreBlind), documents and OCR (ChartQA, DocVQA, SEED-Bench-2-Plus, InfoVQA, OmniDocBench), visual math and logic (BabyVision, MathVision, MathVista), STEM knowledge (AI2D, MMMU, MMMU-Pro, ScienceQA), spatial intelligence (MMSI, ViewSpatial, MindCube, EmbSpatial), remote sensing (FRIEDA, GeoBench, VRSBench-VQA), hallucination alignment (POPE), and medical imaging (PathVQA, PMC-VQA, SLAKE, VQA-RAD).
 ## Training

assets/visual_performance_plot.png CHANGED Viewed

Git LFS Details

SHA256: efa9360abb2f2527c2040e1d7b2fc9802e13bc647de150349d7067de38a4e4a7
Pointer size: 131 Bytes
Size of remote file: 172 kB

Git LFS Details

SHA256: f3fe104ab0b8081a8bd6b41c2f5684349c788c926acbb7d67aa496c87d2c52e2
Pointer size: 131 Bytes
Size of remote file: 136 kB