---
library_name: pytorch
tags:
  - world-model
  - diffusion
  - dit
  - meanflow
  - counter-strike
  - opencs2
---

# CS2 World Model — action-conditioned latent DiT (OpenCS2)

Action-conditioned latent world model for OpenCS2: given a few recent frames and the player's
actions, it predicts the next frame. It never touches pixels — history, target and prediction are
all `32×8×8` latents produced by the frozen [CS2 RAE tokenizer](https://huggingface.co/blanchon/cs2-rae).
Code: [github.com/julien-blanchon/world-model](https://github.com/julien-blanchon/world-model).

- **Dynamics core:** ~205M-param in-context DiT (`hidden=1024`, `depth=16`, `heads=16`,
  `register_tokens=4`, always-on within-frame conv-stem).
- **Transport:** iMeanFlow with plain-Gaussian noise (no OT coupling), schedule-shift `α=2`,
  plain MSE. A frame samples in **one network evaluation (NFE=1)**.
- **Conditioning:** `history_frames=4`, `sequence_frame_gap=1`, action-conditioned.
- **Training:** AdamW lr `2e-4`, warmup 2000, EMA `0.9995`, DIAMOND scheduled sampling with an
  `nas` depth curriculum (1 → 2 → 4) and a context-noise ramp (0.05 → 0.2).

## Files

| File | Description |
|---|---|
| `world-model.pt` | Final world-model checkpoint (`runs/world_model/world-model.pt`). |

## Usage

Requires the matching [CS2 RAE tokenizer](https://huggingface.co/blanchon/cs2-rae) (`d32`) and the
[`world-model`](https://github.com/julien-blanchon/world-model) codebase.

> Internal research checkpoint. Provided as-is, no warranty.