Text Generation
Transformers
PyTorch
JAX
Safetensors
Portuguese
llama
text-generation-inference
Eval Results (legacy)
Instructions to use TucanoBR/Tucano-1b1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TucanoBR/Tucano-1b1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TucanoBR/Tucano-1b1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TucanoBR/Tucano-1b1") model = AutoModelForCausalLM.from_pretrained("TucanoBR/Tucano-1b1", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TucanoBR/Tucano-1b1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TucanoBR/Tucano-1b1" # 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-1b1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TucanoBR/Tucano-1b1
- SGLang
How to use TucanoBR/Tucano-1b1 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-1b1" \ --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-1b1", "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-1b1" \ --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-1b1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TucanoBR/Tucano-1b1 with Docker Model Runner:
docker model run hf.co/TucanoBR/Tucano-1b1
| step,calame_pt,lambada_pt,enem,bluex,oab_exams,assin2_rte,assin2_sts,faquad_nli,hatebr,hatespeech_pt,tweet_br,arc_pt,hellaswag_pt,truthfulqa | |
| 20000,52.26,27.91,20.22,21.56,25.51,45.88,0.9,43.97,36.18,44.25,20.73,27.52,35.02,41.61 | |
| 40000,53.95,28.84,20.71,23.37,23.69,33.33,7.0,43.97,33.59,23.1,35.38,28.8,36.5,40.87 | |
| 60000,53.9,28.62,18.4,24.48,25.97,34.77,7.7,43.97,33.21,41.19,15.07,29.49,37.31,41.54 | |
| 80000,54.77,29.3,20.99,24.76,25.74,33.77,0.98,43.97,32.76,41.23,15.16,28.63,38.7,40.94 | |
| 100000,55.01,30.74,20.85,21.14,24.69,53.43,0.0,43.97,32.65,42.43,20.91,27.86,38.96,41.41 | |
| 120000,54.72,29.07,20.08,21.28,25.28,33.33,0.29,43.97,33.49,22.99,21.19,28.63,39.05,40.39 | |
| 140000,55.44,30.33,21.9,22.53,26.2,33.33,4.57,43.97,35.71,48.5,31.33,28.72,40.17,39.14 | |
| 160000,56.5,30.62,20.22,23.5,23.19,48.56,1.59,43.97,24.33,25.71,15.64,29.23,40.33,43.85 | |
| 180000,55.49,30.39,21.97,24.06,27.74,40.37,2.1,43.97,35.38,26.57,42.82,29.49,40.64,40.63 | |
| 200000,55.49,34.17,20.43,23.09,26.79,46.53,2.01,43.97,26.17,42.99,35.51,29.91,40.84,41.9 | |
| 220000,56.5,33.82,20.85,23.23,25.6,33.33,1.5,43.97,33.56,43.99,45.59,28.8,41.75,40.48 | |
| 240000,56.36,33.01,20.22,24.48,25.47,59.28,3.81,43.97,28.21,41.19,20.73,29.49,41.71,40.13 | |
| 260000,56.7,33.5,20.64,23.78,25.74,55.0,5.87,43.97,25.38,41.65,14.43,29.32,42.07,38.55 | |
| 280000,56.89,31.81,20.57,22.11,25.92,65.27,17.2,43.97,33.21,41.23,33.41,29.66,42.34,39.74 | |
| 300000,56.79,33.84,21.13,24.62,26.29,59.36,18.42,43.97,30.32,41.61,20.73,29.74,42.54,39.99 | |
| 320000,57.42,34.08,20.15,24.62,26.24,62.9,4.53,43.97,30.45,41.23,21.46,29.57,42.84,41.08 | |
| 340000,56.98,33.88,20.36,24.06,26.65,55.38,17.06,43.97,29.42,41.23,29.0,30.09,42.71,40.25 | |
| 360000,56.94,34.47,20.71,24.06,25.83,55.66,15.49,43.97,30.14,41.48,32.04,30.0,42.62,40.32 | |
| 380000,57.56,34.23,20.99,24.62,25.42,61.07,17.93,43.97,28.84,41.23,26.95,30.26,42.46,41.03 | |
| 400000,57.76,34.8,21.13,24.34,26.24,54.06,19.49,43.97,27.73,41.57,32.57,30.09,42.8,41.35 | |
| 420000,57.37,34.02,21.34,24.2,25.47,66.91,13.99,43.97,31.35,41.23,32.75,30.26,42.95,41.23 | |
| 440000,58.14,34.23,20.92,25.03,25.97,58.19,13.86,43.97,30.03,41.23,32.22,29.91,42.88,41.4 | |
| 460000,58.0,35.01,21.83,25.03,25.47,54.52,26.75,43.97,29.72,41.19,31.78,29.74,42.79,41.02 | |
| 480000,58.24,34.7,21.41,23.37,25.97,60.82,24.63,43.97,29.0,41.19,32.18,30.43,42.84,41.59 | |