---
license: cc-by-nc-4.0
base_model: Qwen/Qwen3.5-4B
datasets:
  - CS2CD/CS2CD.Counter-Strike_2_Cheat_Detection
tags:
  - counter-strike
  - cs2
  - cheat-detection
  - gguf
  - onnx
---

# CS2 Overwatch review: models

The two models behind [Overwatch review](https://github.com/magicnothief/cs2-overwatch), an offline reviewer for
Counter-Strike 2 demos that runs on your own PC. The app downloads these files
itself, pinned to one commit and checked against their SHA-256; you do not need
to fetch them by hand.

| file | what it is |
|---|---|
| `detector/scorer.onnx` | a 1D CNN that scores each kill's aim trajectory (136 KB) |
| `detector/scorer.json` | its architecture and the frozen clean-player reference a score is read against |
| `judge/judge-v4.Q4_K_M.gguf` | Qwen3.5-4B fine-tuned (QLoRA) to write a verdict from the evidence, Q4_K_M |

## What they are for

To help a person review a demo: which players and which kills deserve a look,
and why, in terms that can be checked in the demo. Not to ban anyone
automatically. A high score says a player's kills look unlike clean players'
kills in the training data; it is evidence to examine, not proof.

## How they were made

- **Detector:** trained on CS2CD (795 matches, 317 with a VAC-banned player);
  per-player ROC-AUC 0.93 in match-grouped cross-validation. Line of sight comes
  from ray casts against each map's collision mesh, not the game's spotting flag,
  which is biased against snipers.
- **Judge (v4):** fine-tuned on generated verdicts whose targets depend only on
  evidence shown in the text (never on the ban label), with clean players' 95th
  and 99th percentiles printed beside every measurement. On 206 held-out cases it
  matches its targets 92% of the time, convicts 29% of banned players, accuses
  2.8% of clean-labelled ones (each where the evidence itself is past the clean
  99th percentile), and cites no number absent from the evidence. On 341 pro
  players from 35 HLTV matches it accused none.

## Credits and licences

- These models are released under
  [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/): free to use,
  share and adapt for non-commercial purposes, with credit. The app's code is
  AGPL-3.0-or-later.
- The judge is a fine-tune of [Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B)
  by the Qwen team, licensed under Apache-2.0; its licence is included as
  `judge/LICENSE-Qwen3.5-Apache-2.0.txt`.
- Both models were trained on the
  [CS2CD dataset](https://huggingface.co/datasets/CS2CD/CS2CD.Counter-Strike_2_Cheat_Detection)
  (CC-BY-4.0) by Mille Mei Zhen Loo and Gert Lužkov.