Instructions to use maritaca-ai/sabia-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maritaca-ai/sabia-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="maritaca-ai/sabia-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("maritaca-ai/sabia-7b") model = AutoModelForCausalLM.from_pretrained("maritaca-ai/sabia-7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use maritaca-ai/sabia-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "maritaca-ai/sabia-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maritaca-ai/sabia-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/maritaca-ai/sabia-7b
- SGLang
How to use maritaca-ai/sabia-7b 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 "maritaca-ai/sabia-7b" \ --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": "maritaca-ai/sabia-7b", "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 "maritaca-ai/sabia-7b" \ --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": "maritaca-ai/sabia-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use maritaca-ai/sabia-7b with Docker Model Runner:
docker model run hf.co/maritaca-ai/sabia-7b
BERTimbau replacement for domain-specific text classification in Portuguese
Hi,
I'm starting this discussion as I currently have fine-tuned three BERTimbau base models for text classification in a Social Listening project. Now that the beta version was successfully released, I'm looking further to improve the overall performance of the project - so, I'm considering two other options:
• Build a simple context based agent using this model along with LangChain;
• Try something around Zero-Shot Classification.
So, I would like to ask if Sabia would be a good fit - as well as if any of these options above are reasonable and make sense.
Best,
Naomi Lago
Notes:
- The project uses Brazilian Portuguese data, hence I do have the need to find relevant models that could also perform well in this language.
- I'm new to this field, so I'd really appreciate any resource recommendations and guidance, in case I missed something.