Instructions to use safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT with Transformers:

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

pipe = pipeline("text-generation", model="safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT")
model = AutoModelForCausalLM.from_pretrained("safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT")
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 safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT

SGLang

How to use safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT 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 "safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT" \
    --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": "safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT",
		"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 "safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT" \
        --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": "safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT with Docker Model Runner:
```
docker model run hf.co/safouaneelg/Apertus-8B-Instruct-2509-AQUA-RAT-SFT
```

safouaneelg commited on Sep 5, 2025

Commit

3444b13

verified ·

1 Parent(s): 589c12a

update model card

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -31,7 +31,9 @@ Check out the model info here: [Swiss-AI/LLM](https://huggingface.co/collections
 # Finetuned on AQUA-RAT
 This repo contains the fine-tuned version of Apertus on [AQuA-RAT dataset](https://huggingface.co/datasets/deepmind/aqua_rat).
 The fine-tuning was performed using Unsloth on one GPU (RTX A6000 48 GB) with the following parameters:
 - per_device_train_batch_size: 8
 - gradient_accumulation_steps: 4 (effective batch size: 32)
 - warmup_steps: 10
@@ -46,7 +48,7 @@ The fine-tuning was performed using Unsloth on one GPU (RTX A6000 48 GB) with th
 - eval_strategy: steps
 - eval_steps: 150
 - packing: True
--
 ## How to use
 You can run this fine-tuned version using the below instructions:

 # Finetuned on AQUA-RAT
 This repo contains the fine-tuned version of Apertus on [AQuA-RAT dataset](https://huggingface.co/datasets/deepmind/aqua_rat).
 The fine-tuning was performed using Unsloth on one GPU (RTX A6000 48 GB) with the following parameters:
 - per_device_train_batch_size: 8
 - gradient_accumulation_steps: 4 (effective batch size: 32)
 - warmup_steps: 10
 - eval_strategy: steps
 - eval_steps: 150
 - packing: True
 ## How to use
 You can run this fine-tuned version using the below instructions: