Instructions to use gaparecido/apertus-8b-financial-reasoner-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gaparecido/apertus-8b-financial-reasoner-v2 with Transformers:

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

pipe = pipeline("text-generation", model="gaparecido/apertus-8b-financial-reasoner-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gaparecido/apertus-8b-financial-reasoner-v2")
model = AutoModelForCausalLM.from_pretrained("gaparecido/apertus-8b-financial-reasoner-v2", 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 gaparecido/apertus-8b-financial-reasoner-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gaparecido/apertus-8b-financial-reasoner-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gaparecido/apertus-8b-financial-reasoner-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gaparecido/apertus-8b-financial-reasoner-v2

SGLang

How to use gaparecido/apertus-8b-financial-reasoner-v2 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 "gaparecido/apertus-8b-financial-reasoner-v2" \
    --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": "gaparecido/apertus-8b-financial-reasoner-v2",
		"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 "gaparecido/apertus-8b-financial-reasoner-v2" \
        --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": "gaparecido/apertus-8b-financial-reasoner-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use gaparecido/apertus-8b-financial-reasoner-v2 with Docker Model Runner:
```
docker model run hf.co/gaparecido/apertus-8b-financial-reasoner-v2
```

apertus-8b-financial-reasoner-v2

A fine-tune of swiss-ai/Apertus-8B-Instruct-2509 for two-stage financial analysis of a stock ticker:

Task A – classify how the market reacted to a news item given the price move (good, bad, neutral, overreaction_down, overreaction_up).
Task B – given that reaction, a valuation gap and fundamentals, write the reasoning to find a recommendation (BUY/SELL/HOLD) and answer as JSON.

Format

Full merged checkpoint in bfloat16 (~16 GB, 4 safetensors shards). It is not pre-quantized — load it in 4-bit at runtime if you need to fit a small GPU:

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "gaparecido/apertus-8b-financial-reasoner-v2",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)
model.config.use_cache = True
model.generation_config.use_cache = True

Serving notes

- Needs a bf16-capable GPU (L4 / A10G / A100 or better). Apertus is bf16-trained; in fp16 on a T4 the logits overflow to NaN and every generated token is <unk>.
- The upstream Apertus config ships use_cache: false and this repo has no generation_config.json to override it, so pin use_cache=True (as above) or generation recomputes attention over the full sequence per token.
- The CUDA-fused xIELU not available warning is harmless — the Python fallback costs ~10% throughput.

Training

Trained with Unsloth (https://github.com/unslothai/unsloth) (QLoRA, 4-bit) and Hugging Face TRL, loaded from Unsloth's unsloth/apertus-8b-instruct-2509-unsloth-bnb-4bit mirror of the base model, on an NVIDIA L4.

Downloads last month: 26

Model tree for gaparecido/apertus-8b-financial-reasoner-v2

Base model

swiss-ai/Apertus-8B-2509

Finetuned

swiss-ai/Apertus-8B-Instruct-2509

Finetuned

(19)

this model