Instructions to use amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental with Transformers:

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

pipe = pipeline("text-generation", model="amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental")
model = AutoModelForMultimodalLM.from_pretrained("amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental

SGLang

How to use amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental 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 "amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental" \
    --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": "amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental",
		"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 "amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental" \
        --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": "amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental with Docker Model Runner:
```
docker model run hf.co/amadeusai/Amadeus-Verbo-BI-Qwen-2.5-0.5B-PT-BR-Instruct-Experimental
```

wacc2 commited on Jun 3, 2025

Commit

6f2e01e

verified ·

1 Parent(s): 1d990fc

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -7

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ license: apache-2.0
 ###  Amadeus-Verbo-BI-Qwen2.5-0.5B-PT-BR-Instruct
 #### Introduction
 Amadeus-Verbo-BI-Qwen2.5-0.5B-PT-BR-Instruct is a Brazilian-Portuguese language model (PT-BR-LLM) developed from the base model Qwen2.5-0.5B through fine-tuning, for 2 epochs, with 600k instructions dataset.
-Read our article [here](https://www.).
 ## Details
@@ -125,11 +125,13 @@ print(completion[0]['generated_text'])
 If you find our work helpful, feel free to cite it.
 ```
-@misc{Amadeus AI,
-    title = {Amadeus Verbo: A Brazilian Portuguese large language model.},
-    url = {https://amadeus-ai.com},
-    author = {Amadeus AI},
-    month = {November},
-    year = {2024}
 }
 ```

 ###  Amadeus-Verbo-BI-Qwen2.5-0.5B-PT-BR-Instruct
 #### Introduction
 Amadeus-Verbo-BI-Qwen2.5-0.5B-PT-BR-Instruct is a Brazilian-Portuguese language model (PT-BR-LLM) developed from the base model Qwen2.5-0.5B through fine-tuning, for 2 epochs, with 600k instructions dataset.
+Read our article [here](https://arxiv.org/abs/2506.00019).
 ## Details
 If you find our work helpful, feel free to cite it.
 ```
+@misc{cruzcastañeda2025amadeusverbotechnicalreportpowerful,
+      title={Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese},
+      author={William Alberto Cruz-Castañeda and Marcellus Amadeus},
+      year={2025},
+      eprint={2506.00019},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2506.00019},
 }
 ```