Instructions to use LesterCerioli/LLM-GO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LesterCerioli/LLM-GO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LesterCerioli/LLM-GO")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("LesterCerioli/LLM-GO", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use LesterCerioli/LLM-GO with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LesterCerioli/LLM-GO" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LesterCerioli/LLM-GO", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LesterCerioli/LLM-GO
- SGLang
How to use LesterCerioli/LLM-GO 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 "LesterCerioli/LLM-GO" \ --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": "LesterCerioli/LLM-GO", "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 "LesterCerioli/LLM-GO" \ --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": "LesterCerioli/LLM-GO", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LesterCerioli/LLM-GO with Docker Model Runner:
docker model run hf.co/LesterCerioli/LLM-GO
| # scripts/deploy_huggingface.sh — publica o GoLLM no Hugging Face Hub | |
| set -euo pipefail | |
| : "${HF_TOKEN:?Defina HF_TOKEN antes de executar}" | |
| : "${HF_REPO_ID:?Defina HF_REPO_ID (ex: meu-org/llm-go-350m)}" | |
| CKPT_DIR=${CKPT_DIR:-checkpoints/final} | |
| TOK_DIR=${TOK_DIR:-data/tokenizer} | |
| PRIVATE=${PRIVATE:-false} | |
| COMMIT_MSG=${COMMIT_MSG:-"Upload GoLLM checkpoint"} | |
| if [ ! -f "$CKPT_DIR/config.json" ]; then | |
| echo "ERRO: Checkpoint não encontrado em $CKPT_DIR." | |
| exit 1 | |
| fi | |
| echo "==> Publicando GoLLM no Hugging Face Hub" | |
| echo " repo : $HF_REPO_ID" | |
| echo " ckpt : $CKPT_DIR" | |
| echo " tok : $TOK_DIR" | |
| echo " privado: $PRIVATE" | |
| echo "" | |
| llm-go-deploy \ | |
| --ckpt-dir "$CKPT_DIR" \ | |
| --tok-dir "$TOK_DIR" \ | |
| --repo-id "$HF_REPO_ID" \ | |
| --token "$HF_TOKEN" \ | |
| --message "$COMMIT_MSG" \ | |
| $([ "$PRIVATE" = "true" ] && echo "--private" || echo "--public") | |
| echo "" | |
| echo "✅ Modelo publicado em: https://huggingface.co/$HF_REPO_ID" | |