Text Generation
Transformers
Portuguese
refaunacao
biodiversidade
conservacao
mata-atlantica
portuguese
Instructions to use Refauna/tapirus-open-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Refauna/tapirus-open-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Refauna/tapirus-open-4b")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Refauna/tapirus-open-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Refauna/tapirus-open-4b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Refauna/tapirus-open-4b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Refauna/tapirus-open-4b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Refauna/tapirus-open-4b
- SGLang
How to use Refauna/tapirus-open-4b 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 "Refauna/tapirus-open-4b" \ --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": "Refauna/tapirus-open-4b", "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 "Refauna/tapirus-open-4b" \ --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": "Refauna/tapirus-open-4b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Refauna/tapirus-open-4b with Docker Model Runner:
docker model run hf.co/Refauna/tapirus-open-4b
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ datasets:
|
|
| 15 |
- refauna/refauna-sft-v0.1
|
| 16 |
---
|
| 17 |
|
| 18 |
-
#
|
| 19 |
|
| 20 |
Modelo especializado em refaunação, conservação da biodiversidade
|
| 21 |
e restauração de interações ecológicas.
|
|
|
|
| 15 |
- refauna/refauna-sft-v0.1
|
| 16 |
---
|
| 17 |
|
| 18 |
+
# Tapirus Open 4B v0.1
|
| 19 |
|
| 20 |
Modelo especializado em refaunação, conservação da biodiversidade
|
| 21 |
e restauração de interações ecológicas.
|