GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
OmniJev
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
OmniJev
Model Tree
Qwen/Qwen3.5-0.8B-Base
Input Modalities
Output Modalities
Supported Functionality
One model, one prompt, ten games. Every tile opens that game on the demo with the model playing; the number under each is its score against the teacher (1.00 = matches the teacher, 0 = random play).
16 held-out episodes per game, argmax move, episodes capped at 1500 steps. Random play and the teacher run the same seeds through the same harness. vs teacher is (model - random) / (teacher - random), so 0 is random play and 1.00 is the teacher. In the chart the light bars are behaviour cloning and the first DAgger round, the dark bar is this release.
| Game | Random | PlayJev | Teacher | vs teacher |
|---|---|---|---|---|
| 👾 Space Invaders | 215 | 400 | 400 | 1.00 |
| 🏎️ Racer | 238 | 6707 | 6712 | 1.00 |
| 📦 Sokoban | 6.6 | 102.1 | 102.2 | 1.00 |
| 🐍 Snake | 1.0 | 89.5 | 114 | 0.79 |
| 👻 Pacman | 113 | 3702 | 7026 | 0.52 |
| 🍄 Infinite Mario | 613 | 1764 | 4229 | 0.32 |
| 🧱 Tetris | 162 | 4718 | 15288 | 0.30 |
| 🐦 Floppy Bird | 0.0 | 13.8 | 84.0 | 0.16 |
| 🧊 Breakout | 496 | 2712 | 16547 | 0.14 |
| 🔢 2048 | 1021 | 3386 | 19593 | 0.13 |
| mean | 0.53 |
The model never sees a game's name. It sees the current frame and the list of moves, and it answers with one of them.
The input is the current frame and the list of moves, rendered with the frozen OpenJev prompt. The answer is
the single token after Answer:, and the probability over moves is the softmax over the option letters at
that position: one forward pass, no sampling, nothing generated. Moves are shuffled in every training sample,
so position carries no information. Where velocity matters the vision tower also takes the previous frame, at
no extra token cost.
The demo's single game view is the whole model in one picture: the frame on the left is the only input, the bars are what the forward pass returns, the line below them is how sure it was at every step so far.
python
from playjev.model import PlayJevModel # github.com/OmniJev/PlayJevmodel = PlayJevModel("OmniJev/PlayJev-0.8B").load()d = model.decide([frame], options)[0] # one forward pass, a probability per moved.choice, d.probs, d.confidence # the move it takes, the distribution, how sure it is
The prompt, the readout and the option format are built in playjev/model.py, and the demo prints the exact prompt for every game.
One program per game (BFS, expectimax, placement search, A* with deadlock pruning, physics search) plays on the game's internal state and labels frames with a soft target. The model trains on 863k such frames, then on two DAgger rounds where it plays 40k frames per game and the teachers relabel what it visited. Full fine-tuning, one epoch per round, batch 64, learning rate 2e-5, fp32 master weights with bf16 autocast. The trainer is playjev/train_sft.py.
Apache-2.0, same as the base model. The ten games are other people's work and stay in the code repository under their own licences.