Update model file path in ModelManager; change from poeticagpt-quantized-new.pth to poeticagpt.pth

Fix logging issues in poetry_generation.log; add warnings for custom vocabulary loading and model file not found errors, and ensure BASE_MODEL_DIR ends with a slash

Refactor logging setup in main.py; improve file handler configuration with fallback to stdout and update model path

Add model files and tokenizer configuration; include special tokens and initialization settings

Refactor GenerateRequest model; remove field aliases for emotional_tone, creative_style, language_variety, and word_repetition, and update validation error messages to match new field names

Refactor GenerateRequest model; update emotional_tone field alias and improve field definitions for clarity

Refactor GenerateRequest model; remove unnecessary aliases for emotional_tone and word_repetition fields

Refactor GenerateRequest model; update field names to snake_case, add aliases, and improve validation methods

Enhance model initialization and download process; add directory verification, error handling, and temporary file management

Refactor model initialization logic; improve error handling and logging for better diagnostics

Implement model initialization and health check endpoints; add model download logic, error handling, and request validation

Add FastAPI app initialization in main.py

Refactor model path handling in main.py; define BASE_DIR and MODEL_DIR, ensure model directory exists, and set model download URL

Fix import statement for MODEL_PATH in main.py to reflect updated module structure

Enhance model initialization and error handling; implement model path verification, improve logging configuration, and modify startup event for better diagnostics

Update model configuration and enhance initialization logic; adjust BASE_DIR for container, implement model download functionality, and improve health check response

Set permissions for /app directory in Dockerfile

Fix import statement for MODEL_PATH in main.py

Enhance Poetry Generator API; implement health check endpoint, improve model loading with logging, and update request/response models

Refactor poem generation logic; implement lazy loading for model and update request/response models

Remove redundant model initialization parameters for improved clarity

Remove python-multipart dependency from requirements.txt

Update dependencies in requirements.txt; upgrade FastAPI and Uvicorn, add new libraries for model handling and API requests

Refactor FastAPI application structure; implement CORS middleware, update model initialization, and enhance poem generation endpoint with new request and response models

Implement model preloading in PoetryGenerationService for faster startup; remove redundant preload method from ModelManager

Remove unused import of PoetryGenerationService to clean up code

Refactor poem generation parameters; replace PoemRequest with GenerationParams for enhanced control and validation of generation settings

Remove temperature parameter from generate_poem function call for simplified text generation

Refactor ModelManager and PoetryGenerationService for CPU optimization; enhance model initialization, improve text generation parameters, and implement explicit resource cleanup

Refactor PoetryGenerationService and ModelManager for CPU optimization; update model and tokenizer initialization, simplify prompt templates, and enhance text generation and cleaning processes

Update generate_poem function to use max_new_tokens for improved token control

Refactor PoetryGenerationService to improve model preloading and poem generation; switch to max_new_tokens for better control and update model name for consistency

Add model preloading functionality to PoetryGenerationService for improved startup efficiency and error handling

Refactor PoetryGenerationService to enhance poem generation; switch to GPT2-medium model, improve prompt templates, and implement output cleaning for better formatting and quality

Refactor pipeline initialization in ModelManager to use device_map for automatic device selection

Update model name in PoetryGenerationService to use distilbert/distilgpt2 for improved compatibility in low-resource environments

Refactor PoetryGenerationService and ModelManager for improved resource efficiency; optimize model loading, implement caching, and enhance error handling

Add bitsandbytes to requirements for enhanced model performance

Optimize model loading and error handling in PoetryGenerationService; implement async poem generation and enhance application startup process

Improve model preloading in PoetryGenerationService with meaningful return value and enhanced error handling

Refactor PoetryGenerationService to streamline model initialization and improve error handling

Set HF_HOME environment variable for caching in Dockerfile

Enhance lifespan management in FastAPI by initializing PoetryGenerationService and handling model preloading asynchronously

fixes

Refactor model loading to use a consistent model name variable in PoetryGenerationService

Fix variable name for model loading in PoetryGenerationService

Add model preloading functionality to PoetryGenerationService and initialize on startup

Update model name in ModelManager to Llama-3.2-1B-Instruct

Remove optimized module usage from poetry generation service

Remove optimized module usage from poetry generation and downgrade PyTorch version to 2.3.1