Instructions to use aquas-modela/Aqua-1.0.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aquas-modela/Aqua-1.0.0 with Transformers:

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

pipe = pipeline("text-generation", model="aquas-modela/Aqua-1.0.0")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aquas-modela/Aqua-1.0.0")
model = AutoModelForCausalLM.from_pretrained("aquas-modela/Aqua-1.0.0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aquas-modela/Aqua-1.0.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aquas-modela/Aqua-1.0.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aquas-modela/Aqua-1.0.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aquas-modela/Aqua-1.0.0

SGLang

How to use aquas-modela/Aqua-1.0.0 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 "aquas-modela/Aqua-1.0.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aquas-modela/Aqua-1.0.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "aquas-modela/Aqua-1.0.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aquas-modela/Aqua-1.0.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aquas-modela/Aqua-1.0.0 with Docker Model Runner:
```
docker model run hf.co/aquas-modela/Aqua-1.0.0
```

Aqua is a 100-million-parameter model trained on vast amounts of curated, organized data. It is designed for general-purpose responses and is retrained daily. Its intended use is as a base model for fine-tuning by companies or individuals, and it is released under the Apache 2.0 license for flexible use. Although this version has been trained on highly refined data up to 2026, it is the smallest variant. We will soon launch Aqua-3.0.0, a model optimized for more fluent Spanish conversations, with future plans to add support for English, Chinese, Arabic, and Russian.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
repo = "aquas-modela/Aqua-1.0.0"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo)
inputs = tok("USUARIO: hola\nASISTENTE:", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.78, top_p=0.92, top_k=50, repetition_penalty=1.08, no_repeat_ngram_size=3)
print(tok.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Downloads last month: 234

Safetensors

Model size

0.1B params

Tensor type

F16

aquas-modela
/

Aqua-1.0.0

Usage

Datasets used to train aquas-modela/Aqua-1.0.0