Robert Knight robertknight

Hugging Face Top-200 ONNX Models — RTen Compatibility Sweep

Testing the 200 most-downloaded Hugging Face repos tagged onnx (by download count, snapshot 2026-07-25) against the RTen CLI. Repos 1-100 were covered by the first sweep; 101-200 by a follow-up sweep using the same method.

Method

Models downloaded to hf_models/{repo} and run with target/release/rten <model.onnx> (random inputs).
Dynamic dimensions set with --size, input value ranges with --range (e.g. token IDs must be in vocab range).
Per repo: the main fp32 model (all parts, for encoder/decoder splits) plus one representative

Missing ONNX operators: implementation cost estimates

Rough estimates of the cost of implementing the ONNX operators listed as unsupported in the operator tracking issue, based on the ONNX operator specs. Last updated: 2026-07-12.

How to read the estimates

Complexity is Small / Medium / Large, judging spec surface area

rten ONNX Panic Fuzzing — Findings

Goal: find ONNX models that make cargo run -p rten-cli -r -- <model> panic or crash (not return a clean error). A panic where ONNX Runtime returns a clean error still counts as a robustness bug. Clean Err returns from rten do not count.

Harness: /tmp/rten-fuzz/ — harness.py builds models, runs ORT (validity check) then rten, and flags crashes. Binary: target/release/rten.

Severity scale

Session Prompts

Review the code for the ocrs-cli crate which is a CLI tool for OCR. Then make a plan to implement a new feature which will allow processing images taken from the system clipboard. The feature should be behind a clipboard Cargo feature which is disabled by default. To read from the clipboard, the arboard crate (https://docs.rs/arboard/latest/arboard/) should be used.
`Implement the following plan:

Plan: Clipboard Support for ocrs-cli

Overview

General development notes

This document contains general instructions for agents making changes in Hypothesis projects.

Frontend

Our frontend tech stack uses TypeScript, Preact and Tailwind CSS.

After editing code, run yarn format
To check for errors, run yarn typecheck and yarn lint

	#!/usr/bin/env python3

	import argparse
	import json
	import os
	import sys
	import time
	from datetime import datetime, timezone
	from typing import List, Dict, Any, Optional

	<html>
	<body>
	<div id="app"></div>
	<script type="importmap">
	{
	"imports": {
	"preact": "https://unpkg.com/preact@10.25.4/dist/preact.module.js",
	"preact/hooks": "https://unpkg.com/preact@10.25.4/hooks/dist/hooks.module.js"
	}
	}

	import getpass
	import json
	import re
	import sys

	import requests

	GROUP_URL_PATTERN = "https://hypothes.is/groups/([^/]+)/.*"

	api_token = getpass.getpass(

	# Analysis of Hypothesis Python app routes as part of
	# https://github.com/hypothesis/playbook/issues/1797#issuecomment-2397242000.

	import os
	import ast
	import sys


	def find_py_files(root_dir):
	excluded_dirs = ["node_modules", "build", "test", "tests", "third_party"]

	# Script to fetch and print the transcript for a YouTube video using the
	# YouTube Data API v3.
	#
	# 1. Create a project in the Google API Console
	# 2. Enable the YouTube Data API v3 for the new project
	# 3. Create credentials for a "Desktop" OAuth client. Download the JSON file
	# containing the credentials at the end of the setup process.
	# 4. Create a new virtualenv and install dependencies with:
	#
	# ```