Text Generation
Transformers
Burmese
English
myanmar
burmese
llm
chat
instruction-following
conversational
autoregressive
Instructions to use amkyawdev/myanmar-ghost with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amkyawdev/myanmar-ghost with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="amkyawdev/myanmar-ghost") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("amkyawdev/myanmar-ghost", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use amkyawdev/myanmar-ghost with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "amkyawdev/myanmar-ghost" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amkyawdev/myanmar-ghost", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/amkyawdev/myanmar-ghost
- SGLang
How to use amkyawdev/myanmar-ghost 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 "amkyawdev/myanmar-ghost" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amkyawdev/myanmar-ghost", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "amkyawdev/myanmar-ghost" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amkyawdev/myanmar-ghost", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use amkyawdev/myanmar-ghost with Docker Model Runner:
docker model run hf.co/amkyawdev/myanmar-ghost
| """Logging utilities for Myanmar Ghost project.""" | |
| import logging | |
| import sys | |
| from datetime import datetime | |
| from pathlib import Path | |
| from typing import Optional | |
| from loguru import logger as _logger | |
| def setup_logger( | |
| name: str = "myanmar_ghost", | |
| log_dir: Optional[str] = None, | |
| level: str = "INFO", | |
| format: str = None, | |
| ) -> logging.Logger: | |
| """Set up logger with file and console output. | |
| Args: | |
| name: Logger name | |
| log_dir: Directory for log files | |
| level: Logging level | |
| format: Custom log format | |
| Returns: | |
| Configured logger | |
| """ | |
| if format is None: | |
| format = ( | |
| "<green>{time:YYYY-MM-DD HH:mm:ss}</green> | " | |
| "<level>{level: <8}</level> | " | |
| "<cyan>{name}</cyan>:<cyan>{function}</cyan>:<cyan>{line}</cyan> | " | |
| "<level>{message}</level>" | |
| ) | |
| # Remove default handler | |
| _logger.remove() | |
| # Console output | |
| _logger.add( | |
| sys.stdout, | |
| format=format, | |
| level=level, | |
| colorize=True, | |
| ) | |
| # File output | |
| if log_dir: | |
| log_path = Path(log_dir) | |
| log_path.mkdir(parents=True, exist_ok=True) | |
| timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") | |
| log_file = log_path / f"{name}_{timestamp}.log" | |
| _logger.add( | |
| log_file, | |
| format=format, | |
| level=level, | |
| rotation="100 MB", | |
| retention="30 days", | |
| compression="zip", | |
| ) | |
| return _logger | |
| def get_logger(name: str = None) -> logging.Logger: | |
| """Get logger instance. | |
| Args: | |
| name: Logger name (optional) | |
| Returns: | |
| Logger instance | |
| """ | |
| return _logger | |
| class TrainingLogger: | |
| """Logger for training metrics and progress.""" | |
| def __init__( | |
| self, | |
| log_dir: str = "outputs/logs", | |
| experiment_name: str = "experiment", | |
| ): | |
| self.log_dir = Path(log_dir) | |
| self.log_dir.mkdir(parents=True, exist_ok=True) | |
| self.experiment_name = experiment_name | |
| self.metrics_history = [] | |
| timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") | |
| self.log_file = self.log_dir / f"{experiment_name}_{timestamp}.log" | |
| def log_metrics(self, metrics: dict, step: int) -> None: | |
| """Log metrics at a specific step.""" | |
| entry = { | |
| "step": step, | |
| "timestamp": datetime.now().isoformat(), | |
| **metrics, | |
| } | |
| self.metrics_history.append(entry) | |
| log_line = f"Step {step}: " + ", ".join( | |
| f"{k}={v:.4f}" if isinstance(v, float) else f"{k}={v}" | |
| for k, v in metrics.items() | |
| ) | |
| _logger.info(log_line) | |
| def log_epoch(self, epoch: int, metrics: dict) -> None: | |
| """Log metrics at epoch end.""" | |
| entry = { | |
| "epoch": epoch, | |
| "timestamp": datetime.now().isoformat(), | |
| **metrics, | |
| } | |
| self.metrics_history.append(entry) | |
| log_line = f"Epoch {epoch}: " + ", ".join( | |
| f"{k}={v:.4f}" if isinstance(v, float) else f"{k}={v}" | |
| for k, v in metrics.items() | |
| ) | |
| _logger.info(log_line) | |
| def save_history(self) -> str: | |
| """Save metrics history to file.""" | |
| import json | |
| with open(self.log_file, "w", encoding="utf-8") as f: | |
| json.dump(self.metrics_history, f, indent=2) | |
| return str(self.log_file) | |
| if __name__ == "__main__": | |
| logger = setup_logger("test_logger", "outputs/logs") | |
| logger.info("Logger initialized successfully") | |