Image-Text-to-Text
Transformers
Safetensors
English
gamescaling
game-agent
embodied-agent
keyboard-mouse
continued-pretraining
qwen3_5
Instructions to use THUSI-Lab/GameScaling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use THUSI-Lab/GameScaling with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="THUSI-Lab/GameScaling")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("THUSI-Lab/GameScaling", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use THUSI-Lab/GameScaling with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "THUSI-Lab/GameScaling" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "THUSI-Lab/GameScaling", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/THUSI-Lab/GameScaling
- SGLang
How to use THUSI-Lab/GameScaling with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "THUSI-Lab/GameScaling" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "THUSI-Lab/GameScaling", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "THUSI-Lab/GameScaling" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "THUSI-Lab/GameScaling", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use THUSI-Lab/GameScaling with Docker Model Runner:
docker model run hf.co/THUSI-Lab/GameScaling
Model card: narrower message block
Browse files
README.md
CHANGED
|
@@ -188,7 +188,8 @@ asterisks.
|
|
| 188 |
### Complete example: Doom Battle-1
|
| 189 |
|
| 190 |
This is the full system prompt for the ViZDoom Battle-1 map, as in
|
| 191 |
-
`prompts/example_doom_battle1.txt`. It is the same text in both reasoning modes (§4).
|
|
|
|
| 192 |
|
| 193 |
```text
|
| 194 |
You are a gaming expert, and you are currently playing Doom Battle-1. You are proficient in keyboard and mouse operations. You understand game mechanics and combat pacing, can quickly extract key information from the current screen, and can think and make precise decisions at critical moments. Based on the current screen, plan the next 200ms of actions, consisting of 6 steps spaced 33ms apart. Each step lasts 33ms, until the next step begins. If the current situation continues the previous strategy, output the action directly. Think only when the situation changes significantly, the previous analysis is no longer valid, or a new objective appears.
|
|
@@ -311,11 +312,11 @@ Each user turn is the text `current game screen` followed by the frame. Multi-tu
|
|
| 311 |
|
| 312 |
```text
|
| 313 |
system system prompt (§2)
|
| 314 |
-
user "current game screen" + frame t-k
|
| 315 |
-
assistant action taken at t-k
|
| 316 |
-
...
|
| 317 |
user "current game screen" + current frame
|
| 318 |
-
assistant
|
| 319 |
```
|
| 320 |
|
| 321 |
Past turns keep only the action (`history_think=0`). A turn that failed to parse is stored as an
|
|
|
|
| 188 |
### Complete example: Doom Battle-1
|
| 189 |
|
| 190 |
This is the full system prompt for the ViZDoom Battle-1 map, as in
|
| 191 |
+
`prompts/example_doom_battle1.txt`. It is the same text in both reasoning modes (§4). Long
|
| 192 |
+
lines scroll horizontally; each line break below is a real `\n` in the prompt.
|
| 193 |
|
| 194 |
```text
|
| 195 |
You are a gaming expert, and you are currently playing Doom Battle-1. You are proficient in keyboard and mouse operations. You understand game mechanics and combat pacing, can quickly extract key information from the current screen, and can think and make precise decisions at critical moments. Based on the current screen, plan the next 200ms of actions, consisting of 6 steps spaced 33ms apart. Each step lasts 33ms, until the next step begins. If the current situation continues the previous strategy, output the action directly. Think only when the situation changes significantly, the previous analysis is no longer valid, or a new objective appears.
|
|
|
|
| 312 |
|
| 313 |
```text
|
| 314 |
system system prompt (§2)
|
| 315 |
+
user "current game screen" + frame t-k
|
| 316 |
+
assistant action taken at t-k (no reasoning)
|
| 317 |
+
... (last history_len turns, default 5)
|
| 318 |
user "current game screen" + current frame
|
| 319 |
+
assistant "<think>" or "<think>\n\n</think>"
|
| 320 |
```
|
| 321 |
|
| 322 |
Past turns keep only the action (`history_think=0`). A turn that failed to parse is stored as an
|