Text Generation
Transformers
PyTorch
JAX
Safetensors
Portuguese
llama
text-generation-inference
Eval Results (legacy)
Instructions to use TucanoBR/Tucano-630m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TucanoBR/Tucano-630m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TucanoBR/Tucano-630m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TucanoBR/Tucano-630m") model = AutoModelForCausalLM.from_pretrained("TucanoBR/Tucano-630m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TucanoBR/Tucano-630m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TucanoBR/Tucano-630m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TucanoBR/Tucano-630m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TucanoBR/Tucano-630m
- SGLang
How to use TucanoBR/Tucano-630m 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 "TucanoBR/Tucano-630m" \ --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": "TucanoBR/Tucano-630m", "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 "TucanoBR/Tucano-630m" \ --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": "TucanoBR/Tucano-630m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TucanoBR/Tucano-630m with Docker Model Runner:
docker model run hf.co/TucanoBR/Tucano-630m
| { | |
| "results": { | |
| "arc_pt": { | |
| "acc": 0.24444444444444444, | |
| "acc_stderr": 0.012569442967524474, | |
| "acc_norm": 0.28888888888888886, | |
| "acc_norm_stderr": 0.013256439556126792 | |
| }, | |
| "hellaswag_pt": { | |
| "acc": 0.3326470906923827, | |
| "acc_stderr": 0.004904738424240269, | |
| "acc_norm": 0.39408386607433094, | |
| "acc_norm_stderr": 0.00508682495262388 | |
| }, | |
| "truthfulqa_pt": { | |
| "mc1": 0.23604060913705585, | |
| "mc1_stderr": 0.015137046117152837, | |
| "mc2": 0.42762827969970946, | |
| "mc2_stderr": 0.014911010832660198 | |
| } | |
| }, | |
| "versions": { | |
| "arc_pt": 0, | |
| "hellaswag_pt": 1, | |
| "truthfulqa_pt": 1 | |
| }, | |
| "config": { | |
| "model": "hf-auto", | |
| "model_args": "pretrained=/lustre/mlnvme/data/asen_hpc-mula/checkpoints-llama/slurm_job_17032104/step_400000", | |
| "batch_size": 1, | |
| "device": "cuda:0", | |
| "no_cache": false, | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "description_dict": {} | |
| } | |
| } |