Instructions to use PerceptronAI/Isaac-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PerceptronAI/Isaac-0.1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="PerceptronAI/Isaac-0.1", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("PerceptronAI/Isaac-0.1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PerceptronAI/Isaac-0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PerceptronAI/Isaac-0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PerceptronAI/Isaac-0.1",
		"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/PerceptronAI/Isaac-0.1

SGLang

How to use PerceptronAI/Isaac-0.1 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 "PerceptronAI/Isaac-0.1" \
    --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": "PerceptronAI/Isaac-0.1",
		"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 "PerceptronAI/Isaac-0.1" \
        --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": "PerceptronAI/Isaac-0.1",
		"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 PerceptronAI/Isaac-0.1 with Docker Model Runner:
```
docker model run hf.co/PerceptronAI/Isaac-0.1
```

Isaac-0.1

Commit History

HF generation markers

6be5316

philperceptron commited on Apr 13

no newline chat template

af566ad

philperceptron commited on Apr 10

top level vision tower and projector

8c7e248

philperceptron commited on Mar 19

more robust chat template

fe0d275

philperceptron commited on Mar 19

add image pad attr

9cb37ab

philperceptron commited on Mar 18

5.0.0 compatibility, bare Param position embed, sequential removal

3eef895

philperceptron commited on Mar 3

fix: register image processor in auto map

a5d5cc4

philperceptron commited on Jan 7

feat: batch processing/generation

ebbee7e

philperceptron commited on Jan 2

remove sequential

0067217

philperceptron commited on Dec 19, 2025

vision embedding to separate class + revisions

6cdd5dd

philperceptron commited on Dec 17, 2025

Update to add SDPA support

08cbfa9
verified

akshat-perceptron commited on Oct 9, 2025

Add transformers tag and example code snippet (#2)

c10d94a
verified

akshat-perceptron

sergiopaniego HF Staff commited on Sep 18, 2025

Enable AutoProcessor and support latest transformers release (#3)

35afb09
verified

akshat-perceptron

philippguevorguian commited on Sep 18, 2025

Update README.md

0a60a78
verified

akshat-perceptron commited on Sep 17, 2025

Upload folder using huggingface_hub

80c865b
verified

akshat-perceptron commited on Sep 17, 2025

initial commit

50cf804
verified

akshat-perceptron commited on Sep 17, 2025

Commit History

HF generation markers 6be5316

no newline chat template af566ad

top level vision tower and projector 8c7e248

more robust chat template fe0d275

add image pad attr 9cb37ab

5.0.0 compatibility, bare Param position embed, sequential removal 3eef895

fix: register image processor in auto map a5d5cc4

feat: batch processing/generation ebbee7e

remove sequential 0067217

vision embedding to separate class + revisions 6cdd5dd

Update to add SDPA support 08cbfa9 verified

Add transformers tag and example code snippet (#2) c10d94a verified

Enable AutoProcessor and support latest transformers release (#3) 35afb09 verified

Update README.md 0a60a78 verified

Upload folder using huggingface_hub 80c865b verified

initial commit 50cf804 verified

HF generation markers

6be5316

no newline chat template

af566ad

top level vision tower and projector

8c7e248

more robust chat template

fe0d275

add image pad attr

9cb37ab

5.0.0 compatibility, bare Param position embed, sequential removal

3eef895

fix: register image processor in auto map

a5d5cc4

feat: batch processing/generation

ebbee7e

remove sequential

0067217

vision embedding to separate class + revisions

6cdd5dd

Update to add SDPA support

08cbfa9
verified

Add transformers tag and example code snippet (#2)

c10d94a
verified

Enable AutoProcessor and support latest transformers release (#3)

35afb09
verified

Update README.md

0a60a78
verified

Upload folder using huggingface_hub

80c865b
verified

initial commit

50cf804
verified