Instructions to use menezesbruno/manaca-1b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use menezesbruno/manaca-1b-base with Transformers:

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

pipe = pipeline("text-generation", model="menezesbruno/manaca-1b-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("menezesbruno/manaca-1b-base")
model = AutoModelForCausalLM.from_pretrained("menezesbruno/manaca-1b-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use menezesbruno/manaca-1b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "menezesbruno/manaca-1b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "menezesbruno/manaca-1b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/menezesbruno/manaca-1b-base

SGLang

How to use menezesbruno/manaca-1b-base 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 "menezesbruno/manaca-1b-base" \
    --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": "menezesbruno/manaca-1b-base",
		"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 "menezesbruno/manaca-1b-base" \
        --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": "menezesbruno/manaca-1b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use menezesbruno/manaca-1b-base with Docker Model Runner:
```
docker model run hf.co/menezesbruno/manaca-1b-base
```

menezesbruno commited on 7 days ago

Commit

a9f5da7

verified ·

1 Parent(s): 57ae329

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -120,7 +120,7 @@ O Manacá-1B é o modelo mais forte abaixo de 7B na predição da última palavr
 (LAMBADA-PT), empata com os melhores modelos de 1 a 2 B no CALAME-PT, e fica na faixa
 de acaso em ARC-Challenge-PT (como todo modelo base nessa escala). Detalhes, testes
 pareados de McNemar e validação do harness no
-[repositório](https://github.com/Instituto-IA-LNCC/manaca-1b-base) e no [preprint](https://github.com/Instituto-IA-LNCC/manaca-1b-base/blob/main/paper/manaca_1b_base_arxiv.pdf).
 <p align="center">
   <img src="benchmarks_paper_en.png" width="640" alt="Manacá-1B em quatro benchmarks de português, acurácia vs. parâmetros (escala log), com IC95%"/>
@@ -229,7 +229,7 @@ Manacá-1B is the strongest model below 7B on last-word prediction (LAMBADA-PT),
 the best 1-to-2B models on CALAME-PT, and sits near chance on ARC-Challenge-PT (as
 does every base model at this scale). Details, paired McNemar tests, and harness
 validation are in the
-[repository](https://github.com/Instituto-IA-LNCC/manaca-1b-base) and the [preprint](https://github.com/Instituto-IA-LNCC/manaca-1b-base/blob/main/paper/manaca_1b_base_arxiv.pdf).
 <p align="center">
   <img src="benchmarks_paper_en.png" width="640" alt="Manacá-1B across four Portuguese benchmarks, accuracy vs. parameters (log scale), with 95% CIs"/>

 (LAMBADA-PT), empata com os melhores modelos de 1 a 2 B no CALAME-PT, e fica na faixa
 de acaso em ARC-Challenge-PT (como todo modelo base nessa escala). Detalhes, testes
 pareados de McNemar e validação do harness no
+[repositório](https://github.com/Instituto-IA-LNCC/manaca-1b-base) e no [preprint](https://arxiv.org/abs/2608.30114).
 <p align="center">
   <img src="benchmarks_paper_en.png" width="640" alt="Manacá-1B em quatro benchmarks de português, acurácia vs. parâmetros (escala log), com IC95%"/>
 the best 1-to-2B models on CALAME-PT, and sits near chance on ARC-Challenge-PT (as
 does every base model at this scale). Details, paired McNemar tests, and harness
 validation are in the
+[repository](https://github.com/Instituto-IA-LNCC/manaca-1b-base) and the [preprint](https://arxiv.org/abs/2608.30114).
 <p align="center">
   <img src="benchmarks_paper_en.png" width="640" alt="Manacá-1B across four Portuguese benchmarks, accuracy vs. parameters (log scale), with 95% CIs"/>