PanoVLM-500M

PanoVLM is a linear-attention vision-language model: a FastViT-HD vision encoder (timm) feeding a PanoLM linear-attention causal LM through a lightweight projector.

• Type: Vision-Language (image-text-to-text) Model
• LM: PanoLM-380M
• Vision encoder: FastViT-HD (timm), NCHW input
• Projector: BitLinear (encoder dim → LM dim)
• Default image resolution: 1024×1024 (pad-resized; only the resolution is meant to be changed)

Parameters

Component	Parameters
PanoLM LM	~387 M
FastViT-HD vision encoder	~123 M
Projector	~3 M
Total	~513 M

Requirements

torch==2.12.0
transformers==5.8.1
flash-linear-attention==0.5.0
timm==1.0.25

Usage

Replace <repo_id> with the HF Hub identifier.

from transformers import AutoModelForImageTextToText, AutoProcessor
from PIL import Image
import requests

repo_id = "<repo_id>"
model = AutoModelForImageTextToText.from_pretrained(
    repo_id, trust_remote_code=True,
).cuda()
processor = AutoProcessor.from_pretrained(repo_id, trust_remote_code=True)

url = "https://llava-vl.github.io/static/images/view.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(text="<|image|>An image of", images=image,
                   return_tensors="pt").to(model.device)

out = model.generate(**inputs, max_new_tokens=512, temperature=1.0, top_k=10,
                     top_p=1.0, do_sample=True, use_cache=False)
print(processor.decode(out[0], skip_special_tokens=True))