Instructions to use recogna-nlp/phibode_1_5_ultraalpaca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use recogna-nlp/phibode_1_5_ultraalpaca with Transformers:

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

pipe = pipeline("text-generation", model="recogna-nlp/phibode_1_5_ultraalpaca")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("recogna-nlp/phibode_1_5_ultraalpaca")
model = AutoModelForCausalLM.from_pretrained("recogna-nlp/phibode_1_5_ultraalpaca")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use recogna-nlp/phibode_1_5_ultraalpaca with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "recogna-nlp/phibode_1_5_ultraalpaca"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "recogna-nlp/phibode_1_5_ultraalpaca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/recogna-nlp/phibode_1_5_ultraalpaca

SGLang

How to use recogna-nlp/phibode_1_5_ultraalpaca 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 "recogna-nlp/phibode_1_5_ultraalpaca" \
    --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": "recogna-nlp/phibode_1_5_ultraalpaca",
		"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 "recogna-nlp/phibode_1_5_ultraalpaca" \
        --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": "recogna-nlp/phibode_1_5_ultraalpaca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use recogna-nlp/phibode_1_5_ultraalpaca with Docker Model Runner:
```
docker model run hf.co/recogna-nlp/phibode_1_5_ultraalpaca
```

Configuration Parsing Warning:Invalid JSON for config file tokenizer_config.json

Phi-Bode

Phi-Bode Logo

Phi-Bode é um modelo de linguagem ajustado para o idioma português, desenvolvido a partir do modelo base Phi-1.5B fornecido pela Microsoft. Este modelo foi refinado através do processo de fine-tuning utilizando o dataset UltraAlpaca. O principal objetivo deste modelo é ser viável para pessoas que não possuem recursos computacionais disponíveis para o uso de LLMs (Large Language Models). Ressalta-se que este é um trabalho em andamento e o modelo ainda apresenta problemas na geração de texto em português.

Características Principais

Modelo Base: Phi-1.5B, criado pela Microsoft, com 1.3 bilhões de parâmetros.
Dataset para Fine-tuning: UltraAlpaca
Treinamento: O treinamento foi realizado a partir do fine-tuning completo do phi-1.5.

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric	Value
Average	31.95
ENEM Challenge (No Images)	23.58
BLUEX (No Images)	20.72
OAB Exams	24.87
Assin2 RTE	69.07
Assin2 STS	4.94
FaQuAD NLI	43.97
HateBR Binary	34.94
PT Hate Speech Binary	41.23
tweetSentBR	24.19

Downloads last month: 14

Safetensors

Model size

1B params

Tensor type

F32

Space using recogna-nlp/phibode_1_5_ultraalpaca 1

Collection including recogna-nlp/phibode_1_5_ultraalpaca

PhiBode

Collection

PhiBode são modelos baseados na arquitetura Phi, da Microsoft. Aqui, você pode encontrar diversos modelos, sendo eles: • 5 items • Updated Jul 11, 2024

Evaluation results

accuracy on ENEM Challenge (No Images)
Open Portuguese LLM Leaderboard

23.580
accuracy on BLUEX (No Images)
Open Portuguese LLM Leaderboard

20.720
accuracy on OAB Exams
Open Portuguese LLM Leaderboard

24.870
f1-macro on Assin2 RTE
test set Open Portuguese LLM Leaderboard

69.070
pearson on Assin2 STS
test set Open Portuguese LLM Leaderboard

4.940
f1-macro on FaQuAD NLI
test set Open Portuguese LLM Leaderboard

43.970
f1-macro on HateBR Binary
test set Open Portuguese LLM Leaderboard

34.940
f1-macro on PT Hate Speech Binary
test set Open Portuguese LLM Leaderboard

41.230