Instructions to use amogaddy/GenerAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amogaddy/GenerAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="amogaddy/GenerAI")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("amogaddy/GenerAI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use amogaddy/GenerAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "amogaddy/GenerAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amogaddy/GenerAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/amogaddy/GenerAI
- SGLang
How to use amogaddy/GenerAI 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 "amogaddy/GenerAI" \ --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": "amogaddy/GenerAI", "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 "amogaddy/GenerAI" \ --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": "amogaddy/GenerAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use amogaddy/GenerAI with Docker Model Runner:
docker model run hf.co/amogaddy/GenerAI
| import logging | |
| import traceback | |
| import sys | |
| from enum import Enum | |
| # ββ Logging setup βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| LOG_FORMAT = "[%(asctime)s] %(levelname)-8s %(name)s β %(message)s" | |
| DATE_FORMAT = "%H:%M:%S" | |
| logging.basicConfig( | |
| level=logging.DEBUG, | |
| format=LOG_FORMAT, | |
| datefmt=DATE_FORMAT, | |
| handlers=[ | |
| logging.StreamHandler(sys.stdout), | |
| logging.FileHandler("generai.log", encoding="utf-8"), | |
| ], | |
| ) | |
| def get_logger(name: str) -> logging.Logger: | |
| return logging.getLogger(name) | |
| # ββ Error categories βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| class ErrorCode(Enum): | |
| # DB / Knowledge Base | |
| KB_INIT_FAILED = "KB-001" | |
| KB_SEARCH_FAILED = "KB-002" | |
| KB_WRITE_FAILED = "KB-003" | |
| KB_REINFORCE_FAILED = "KB-004" | |
| KB_SEED_FAILED = "KB-005" | |
| # Scraper / Web | |
| WEB_SEARCH_FAILED = "WEB-001" | |
| WEB_FETCH_FAILED = "WEB-002" | |
| WEB_EXTRACT_FAILED = "WEB-003" | |
| WEB_NO_RESULTS = "WEB-004" | |
| # Brain | |
| BRAIN_ASK_FAILED = "BRN-001" | |
| BRAIN_ASYNC_FAILED = "BRN-002" | |
| # UI | |
| UI_INPUT_EMPTY = "UI-001" | |
| UI_HANDLER_FAILED = "UI-002" | |
| class GenerAIError(Exception): | |
| """Base exception with error code and user-friendly message.""" | |
| def __init__(self, code: ErrorCode, detail: str, cause: Exception | None = None): | |
| self.code = code | |
| self.detail = detail | |
| self.cause = cause | |
| super().__init__(f"[{code.value}] {detail}") | |
| def user_message(self) -> str: | |
| cause_str = f"\n> Causa: `{type(self.cause).__name__}: {self.cause}`" if self.cause else "" | |
| return f"β οΈ **Errore {self.code.value}** β {self.detail}{cause_str}" | |
| def log(self, logger: logging.Logger): | |
| logger.error("[%s] %s", self.code.value, self.detail) | |
| if self.cause: | |
| logger.debug("Traceback originale:\n%s", "".join(traceback.format_exception(type(self.cause), self.cause, self.cause.__traceback__))) | |
| def fmt_exc(e: Exception) -> str: | |
| """One-line summary of an exception for log messages.""" | |
| return f"{type(e).__name__}: {e}" | |