Instructions to use matheusrdgsf/phi-sentiment-analysis-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use matheusrdgsf/phi-sentiment-analysis-model with Transformers:

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

pipe = pipeline("text-generation", model="matheusrdgsf/phi-sentiment-analysis-model", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("matheusrdgsf/phi-sentiment-analysis-model", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("matheusrdgsf/phi-sentiment-analysis-model", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use matheusrdgsf/phi-sentiment-analysis-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/matheusrdgsf/phi-sentiment-analysis-model

SGLang

How to use matheusrdgsf/phi-sentiment-analysis-model 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 "matheusrdgsf/phi-sentiment-analysis-model" \
    --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": "matheusrdgsf/phi-sentiment-analysis-model",
		"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 "matheusrdgsf/phi-sentiment-analysis-model" \
        --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": "matheusrdgsf/phi-sentiment-analysis-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use matheusrdgsf/phi-sentiment-analysis-model with Docker Model Runner:
```
docker model run hf.co/matheusrdgsf/phi-sentiment-analysis-model
```

Model Card for Phi 1.5B Microsoft Trained Sentiment Analysis Model

This model performs sentiment analysis on sentences, classifying them as either 'positive' or 'negative'. It is trained on the IMDB dataset and has been fine-tuned for this task.

Model Details

Model Description

Phi 1.5B Microsoft trained with the IMDB Dataset.

Prompt Used in Training

Your task is to classify sentences' sentiment as 'positive' or 'negative'. Your answer should be one word, either 'positive' or 'negative'. Sentence: {text} Answer:

Inference Example using Hugging Face Inference API

from transformers import pipeline

classifier = pipeline("text-classification", model="matheusrdgsf/phi-sentiment-analysis-model")

result = classifier("I love this movie")
print(result[0]['label'])  # Output: 'POSITIVE'

Downloads last month: 13

Safetensors

Model size

1B params

Tensor type

F16