Instructions to use THUSI-Lab/GameScaling-9B-S3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use THUSI-Lab/GameScaling-9B-S3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="THUSI-Lab/GameScaling-9B-S3")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("THUSI-Lab/GameScaling-9B-S3")
model = AutoModelForMultimodalLM.from_pretrained("THUSI-Lab/GameScaling-9B-S3", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use THUSI-Lab/GameScaling-9B-S3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "THUSI-Lab/GameScaling-9B-S3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "THUSI-Lab/GameScaling-9B-S3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/THUSI-Lab/GameScaling-9B-S3

SGLang

How to use THUSI-Lab/GameScaling-9B-S3 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-9B-S3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "THUSI-Lab/GameScaling-9B-S3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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-9B-S3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "THUSI-Lab/GameScaling-9B-S3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use THUSI-Lab/GameScaling-9B-S3 with Docker Model Runner:
```
docker model run hf.co/THUSI-Lab/GameScaling-9B-S3
```

GameScaling-9B-S3 / chat_template.jinja

iTheresaApocalypse

Add files using upload-large-folder tool

df893be verified 21 days ago

Raw History Blame Contribute Delete

7.53 kB

{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
    {%- if content is string %}
        {{- content }}
    {%- elif content is iterable and content is not mapping %}
        {%- for item in content %}
            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
                {%- if is_system_content %}
                    {{- raise_exception('System message cannot contain images.') }}
                {%- endif %}
                {%- if do_vision_count %}
                    {%- set image_count.value = image_count.value + 1 %}
                {%- endif %}
                {%- if add_vision_id %}
                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
                {%- endif %}
                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
            {%- elif 'video' in item or item.type == 'video' %}
                {%- if is_system_content %}
                    {{- raise_exception('System message cannot contain videos.') }}
                {%- endif %}
                {%- if do_vision_count %}
                    {%- set video_count.value = video_count.value + 1 %}
                {%- endif %}
                {%- if add_vision_id %}
                    {{- 'Video ' ~ video_count.value ~ ': ' }}
                {%- endif %}
                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
            {%- elif 'text' in item %}
                {{- item.text }}
            {%- else %}
                {{- raise_exception('Unexpected item type in content.') }}
            {%- endif %}
        {%- endfor %}
    {%- elif content is none or content is undefined %}
        {{- '' }}
    {%- else %}
        {{- raise_exception('Unexpected content type.') }}
    {%- endif %}
{%- endmacro %}
{#- ICLR27-GameScaling CPT permissive template:
    - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。
    - 去掉 assistant 轮的 <think> 注入(该注入依赖全局 last_query_index, 会使
      "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。
    - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array
      传入, `not <ndarray>` 会触发 "truth value of an array ... is ambiguous"。 #}
{%- if tools and tools is iterable and tools is not mapping %}
    {{- '<|im_start|>system\n' }}
    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
    {%- for tool in tools %}
        {{- "\n" }}
        {{- tool | tojson }}
    {%- endfor %}
    {{- "\n</tools>" }}
    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
    {%- if messages[0].role == 'system' %}
        {%- set content = render_content(messages[0].content, false, true)|trim %}
        {%- if content %}
            {{- '\n\n' + content }}
        {%- endif %}
    {%- endif %}
    {{- '<|im_end|>\n' }}
{%- else %}
    {%- if messages[0].role == 'system' %}
        {%- set content = render_content(messages[0].content, false, true)|trim %}
        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
    {%- endif %}
{%- endif %}
{%- for message in messages %}
    {%- set content = render_content(message.content, true)|trim %}
    {%- if message.role == "system" %}
        {%- if not loop.first %}
            {{- raise_exception('System message must be at the beginning.') }}
        {%- endif %}
    {%- elif message.role == "user" %}
        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
    {%- elif message.role == "assistant" %}
        {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码):
            - 若该轮本身已带 <think>(如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入,
              避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。
            - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 <think>\n\n</think>\n\n,
              训练无 think GT 只保结构, 让模型仍会输出 <think>...</think>, 不破坏原生思考通路;
              inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #}
        {%- if '<think>' in content or '</think>' in content %}
            {{- '<|im_start|>' + message.role + '\n' + content }}
        {%- else %}
            {{- '<|im_start|>' + message.role + '\n' + '<think>\n\n</think>\n\n' + content }}
        {%- endif %}
        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
            {%- for tool_call in message.tool_calls %}
                {%- if tool_call.function is defined %}
                    {%- set tool_call = tool_call.function %}
                {%- endif %}
                {%- if loop.first %}
                    {%- if content|trim %}
                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
                    {%- else %}
                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
                    {%- endif %}
                {%- else %}
                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
                {%- endif %}
                {%- if tool_call.arguments is defined %}
                    {%- for args_name, args_value in tool_call.arguments|items %}
                        {{- '<parameter=' + args_name + '>\n' }}
                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
                        {{- args_value }}
                        {{- '\n</parameter>\n' }}
                    {%- endfor %}
                {%- endif %}
                {{- '</function>\n</tool_call>' }}
            {%- endfor %}
        {%- endif %}
        {{- '<|im_end|>\n' }}
    {%- elif message.role == "tool" %}
        {%- if loop.previtem and loop.previtem.role != "tool" %}
            {{- '<|im_start|>user' }}
        {%- endif %}
        {{- '\n<tool_response>\n' }}
        {{- content }}
        {{- '\n</tool_response>' }}
        {%- if not loop.last and loop.nextitem.role != "tool" %}
            {{- '<|im_end|>\n' }}
        {%- elif loop.last %}
            {{- '<|im_end|>\n' }}
        {%- endif %}
    {%- else %}
        {{- raise_exception('Unexpected message role.') }}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|im_start|>assistant\n' }}
{%- endif %}

	{%- set image_count = namespace(value=0) %}
	{%- set video_count = namespace(value=0) %}
	{%- macro render_content(content, do_vision_count, is_system_content=false) %}
	{%- if content is string %}
	{{- content }}
	{%- elif content is iterable and content is not mapping %}
	{%- for item in content %}
	{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
	{%- if is_system_content %}
	{{- raise_exception('System message cannot contain images.') }}
	{%- endif %}
	{%- if do_vision_count %}
	{%- set image_count.value = image_count.value + 1 %}
	{%- endif %}
	{%- if add_vision_id %}
	{{- 'Picture ' ~ image_count.value ~ ': ' }}
	{%- endif %}
	{{- '<\|vision_start\|><\|image_pad\|><\|vision_end\|>' }}
	{%- elif 'video' in item or item.type == 'video' %}
	{%- if is_system_content %}
	{{- raise_exception('System message cannot contain videos.') }}
	{%- endif %}
	{%- if do_vision_count %}
	{%- set video_count.value = video_count.value + 1 %}
	{%- endif %}
	{%- if add_vision_id %}
	{{- 'Video ' ~ video_count.value ~ ': ' }}
	{%- endif %}
	{{- '<\|vision_start\|><\|video_pad\|><\|vision_end\|>' }}
	{%- elif 'text' in item %}
	{{- item.text }}
	{%- else %}
	{{- raise_exception('Unexpected item type in content.') }}
	{%- endif %}
	{%- endfor %}
	{%- elif content is none or content is undefined %}
	{{- '' }}
	{%- else %}
	{{- raise_exception('Unexpected content type.') }}
	{%- endif %}
	{%- endmacro %}
	{#- ICLR27-GameScaling CPT permissive template:
	- 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。
	- 去掉 assistant 轮的 <think> 注入(该注入依赖全局 last_query_index, 会使
	"逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。
	- 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array
	传入, `not <ndarray>` 会触发 "truth value of an array ... is ambiguous"。 #}
	{%- if tools and tools is iterable and tools is not mapping %}
	{{- '<\|im_start\|>system\n' }}
	{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
	{%- for tool in tools %}
	{{- "\n" }}
	{{- tool \| tojson }}
	{%- endfor %}
	{{- "\n</tools>" }}
	{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
	{%- if messages[0].role == 'system' %}
	{%- set content = render_content(messages[0].content, false, true)\|trim %}
	{%- if content %}
	{{- '\n\n' + content }}
	{%- endif %}
	{%- endif %}
	{{- '<\|im_end\|>\n' }}
	{%- else %}
	{%- if messages[0].role == 'system' %}
	{%- set content = render_content(messages[0].content, false, true)\|trim %}
	{{- '<\|im_start\|>system\n' + content + '<\|im_end\|>\n' }}
	{%- endif %}
	{%- endif %}
	{%- for message in messages %}
	{%- set content = render_content(message.content, true)\|trim %}
	{%- if message.role == "system" %}
	{%- if not loop.first %}
	{{- raise_exception('System message must be at the beginning.') }}
	{%- endif %}
	{%- elif message.role == "user" %}
	{{- '<\|im_start\|>' + message.role + '\n' + content + '<\|im_end\|>' + '\n' }}
	{%- elif message.role == "assistant" %}
	{#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码):
	- 若该轮本身已带 <think>(如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入,
	避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。
	- 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 <think>\n\n</think>\n\n,
	训练无 think GT 只保结构, 让模型仍会输出 <think>...</think>, 不破坏原生思考通路;
	inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #}
	{%- if '<think>' in content or '</think>' in content %}
	{{- '<\|im_start\|>' + message.role + '\n' + content }}
	{%- else %}
	{{- '<\|im_start\|>' + message.role + '\n' + '<think>\n\n</think>\n\n' + content }}
	{%- endif %}
	{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
	{%- for tool_call in message.tool_calls %}
	{%- if tool_call.function is defined %}
	{%- set tool_call = tool_call.function %}
	{%- endif %}
	{%- if loop.first %}
	{%- if content\|trim %}
	{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
	{%- else %}
	{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
	{%- endif %}
	{%- else %}
	{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
	{%- endif %}
	{%- if tool_call.arguments is defined %}
	{%- for args_name, args_value in tool_call.arguments\|items %}
	{{- '<parameter=' + args_name + '>\n' }}
	{%- set args_value = args_value \| tojson \| safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value \| string %}
	{{- args_value }}
	{{- '\n</parameter>\n' }}
	{%- endfor %}
	{%- endif %}
	{{- '</function>\n</tool_call>' }}
	{%- endfor %}
	{%- endif %}
	{{- '<\|im_end\|>\n' }}
	{%- elif message.role == "tool" %}
	{%- if loop.previtem and loop.previtem.role != "tool" %}
	{{- '<\|im_start\|>user' }}
	{%- endif %}
	{{- '\n<tool_response>\n' }}
	{{- content }}
	{{- '\n</tool_response>' }}
	{%- if not loop.last and loop.nextitem.role != "tool" %}
	{{- '<\|im_end\|>\n' }}
	{%- elif loop.last %}
	{{- '<\|im_end\|>\n' }}
	{%- endif %}
	{%- else %}
	{{- raise_exception('Unexpected message role.') }}
	{%- endif %}
	{%- endfor %}
	{%- if add_generation_prompt %}
	{{- '<\|im_start\|>assistant\n' }}
	{%- endif %}