Downloads · 30 days
0
paw-interpreter-onnx
lilianahotsko/paw-interpreter-onnx
paw-interpreter-onnx is a machine learning model from lilianahotsko. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for programasweights. The card lists the license as mit.
ONNX runtime models for ProgramAsWeights.
Access
Public
Updated Nov 14, 2025
Repo size
2.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data2.3 GB · 99%
At a glance
- Library
- programasweights
- License
- mit
- Access
- Public
- Created
- Nov 14, 2025
- Updated
- Nov 14, 2025
- SHA
- 180b52e1
Model card
From the Hugging Face model README
paw-interpreter-onnx
ONNX runtime models for ProgramAsWeights.
Model Files
Core (always downloaded):
text_embeddings.onnx- Text tokenizer embeddingsinterpreter.onnx- Main interpreter modeltokenizer/- Fast tokenizer
Optional (lazy loaded):
image_encoder.onnx- Image encoder (CLIP + projection) - only downloaded when using image inputs
Usage
import programasweights as paw
# Text-only program (no Pillow needed!)
fn = paw.function("abc123")
result = fn("Extract emails: [email protected]")
# With images (requires: pip install programasweights[images])
from PIL import Image
img = Image.open("photo.jpg")
result = fn("Count apples:", img)
Installation
# Base install (text-only, ~70MB)
pip install programasweights
# With image support (~85MB)
pip install programasweights[images]
Model Details
- Base model: Qwen2-0.5B
- Runtime: ONNX (lightweight, fast)
- Input: .paw files (prefix KV cache)
- Output: Generated text
- Library
- programasweights
- License
- mit
- Created
- Nov 14, 2025
- Updated
- Nov 14, 2025