Instructions to use WebScraper991923/Affine-S6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WebScraper991923/Affine-S6 with Transformers:

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

pipe = pipeline("text-generation", model="WebScraper991923/Affine-S6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WebScraper991923/Affine-S6")
model = AutoModelForCausalLM.from_pretrained("WebScraper991923/Affine-S6", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WebScraper991923/Affine-S6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WebScraper991923/Affine-S6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WebScraper991923/Affine-S6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WebScraper991923/Affine-S6

SGLang

How to use WebScraper991923/Affine-S6 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 "WebScraper991923/Affine-S6" \
    --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": "WebScraper991923/Affine-S6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "WebScraper991923/Affine-S6" \
        --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": "WebScraper991923/Affine-S6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WebScraper991923/Affine-S6 with Docker Model Runner:
```
docker model run hf.co/WebScraper991923/Affine-S6
```

WebScraper991923 commited on Dec 31, 2025

Commit

b3e23b1

verified ·

1 Parent(s): 08e5ead

Remove duplication footprints

Browse files

Files changed (1) hide show

README.md +0 -3

README.md CHANGED Viewed

@@ -39,10 +39,8 @@ Additionally, to enforce model thinking, the default chat template automatically
 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
 ## Performance
 |  | Qwen3-30B-A3B Thinking | Qwen3-4B Thinking | Qwen3-4B-Thinking-2507 |
 |--- | --- | --- | --- |
 | **Knowledge** | | |
@@ -216,7 +214,6 @@ To achieve optimal performance, we recommend the following settings:
 4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
 ### Citation
 If you find our work helpful, feel free to give us a cite.

 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
 ## Performance
 |  | Qwen3-30B-A3B Thinking | Qwen3-4B Thinking | Qwen3-4B-Thinking-2507 |
 |--- | --- | --- | --- |
 | **Knowledge** | | |
 4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
 ### Citation
 If you find our work helpful, feel free to give us a cite.