Point install instructions at the published PyPI package

README.md

@@ -32,8 +32,10 @@ are frozen, publicly available source models, and only two small projector
 heads (a few million parameters total) were trained from scratch on public
 datasets to align them into a shared space.
 
-📝 Full write-up (how it was built, and seven rounds of what did and didn't
-work): [I Built a Multimodal Embedding Model From Scratch on an RTX 4060](https://medium.com/@mithilmaske/i-built-a-multimodal-embedding-model-from-scratch-on-an-rtx-4060-text-image-audio-and-video-ab1fef04f1cd)
+📦 **`pip install quadembed`** ([PyPI](https://pypi.org/project/quadembed/)) ·
+💻 [Source on GitHub](https://github.com/mithilai/QuadEmbed) ·
+📝 [Full write-up on Medium](https://medium.com/@mithilmaske/i-built-a-multimodal-embedding-model-from-scratch-on-an-rtx-4060-text-image-audio-and-video-ab1fef04f1cd)
+(how it was built, and seven rounds of what did and didn't work)
 
 ## Architecture
 
@@ -91,14 +93,15 @@ as a full narrative write-up on Medium:
 ## Usage
 
 ```bash
-pip install -r requirements.txt
+pip install quadembed          # text + image + audio
+pip install quadembed[video]   # adds video support
 ```
 
 ```python
 from quadembed import QuadEmbed
 from PIL import Image
 
-model = QuadEmbed.from_pretrained("checkpoints")  # auto-detects cuda/cpu
+model = QuadEmbed.from_pretrained()   # downloads these weights automatically
 
 text_embeds = model.embed_text(["a dog running on the beach"])
 image_embeds = model.embed_image([Image.open("photo.jpg").convert("RGB")])
@@ -106,8 +109,16 @@ image_embeds = model.embed_image([Image.open("photo.jpg").convert("RGB")])
 similarity = text_embeds @ image_embeds.T  # already L2-normalized -> cosine similarity
 ```
 
-See `examples/inference_example.py` for a complete runnable script, including
-audio and video usage.
+Each encoder costs memory and download time, so load only what you need:
+
+```python
+model = QuadEmbed.from_pretrained(modalities=("text", "vision"))  # skip audio
+model = QuadEmbed.from_pretrained(device="cpu")                   # force CPU
+```
+
+Audio takes mono float32 arrays at 16 kHz; video takes a file path
+(`model.embed_video_file("clip.mp4")`). See
+`examples/inference_example.py` for a complete runnable script.
 
 ## Important caveat: two different vision checkpoints