Instructions to use rty813/iris-3b-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rty813/iris-3b-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="rty813/iris-3b-bf16", trust_remote_code=True)

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

processor = AutoProcessor.from_pretrained("rty813/iris-3b-bf16", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("rty813/iris-3b-bf16", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rty813/iris-3b-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rty813/iris-3b-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/iris-3b-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rty813/iris-3b-bf16

SGLang

How to use rty813/iris-3b-bf16 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 "rty813/iris-3b-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/iris-3b-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "rty813/iris-3b-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/iris-3b-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rty813/iris-3b-bf16 with Docker Model Runner:
```
docker model run hf.co/rty813/iris-3b-bf16
```

iris-3b-bf16 (bf16)

Full-precision (bf16) PyTorch port of speridlabs/iris-3b, for vLLM / TGI / Xinference / transformers users who don't want the GGUF quant.

Format: pytorch_model.bin (bf16). safetensors conversion in progress.
Architecture: identical to the original — drop-in for AutoModelForCausalLM.from_pretrained("rty813/iris-3b-bf16").
Also loads in vLLM (vllm serve rty813/iris-3b-bf16) and Xinference (search "iris-3b").

Original model card:

license: apache-2.0 library_name: pytorch pipeline_tag: text-to-image tags: - text-to-image - diffusion - pixel-space - flow-matching - general-vision-learner - vision-foundation-model - depth-estimation - image-restoration - super-resolution - arxiv:2610.09450

Iris-3B

Pixel-space generation & general vision learner.
A 3-billion-parameter model that paints every pixel directly — no VAE, no latent space — and, fine-tuned, estimates depth and restores and upscales images.

Downloads last month: 76

Model tree for rty813/iris-3b-bf16

Base model

speridlabs/iris-3b

Finetuned

(4)

this model

Paper for rty813/iris-3b-bf16

Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning

Paper • 2610.09450 • Published 8 days ago • 28