Refactor model loading to use a consistent model name variable in PoetryGenerationService 51ed73b abhisheksan commited on Nov 7, 2024
Fix variable name for model loading in PoetryGenerationService 34aad78 abhisheksan commited on Nov 7, 2024
Add model preloading functionality to PoetryGenerationService and initialize on startup e47369c abhisheksan commited on Nov 7, 2024
Update model name in ModelManager to Llama-3.2-1B-Instruct 5118191 abhisheksan commited on Nov 7, 2024
Remove optimized module usage from poetry generation service 7b5bffa abhisheksan commited on Nov 7, 2024
Remove optimized module usage from poetry generation and downgrade PyTorch version to 2.3.1 ac829a5 abhisheksan commited on Nov 7, 2024
Update Dockerfile and requirements.txt to install PyTorch 2.5.1 and remove redundant numpy installation 904ae2c abhisheksan commited on Nov 7, 2024
Fix Dockerfile to remove duplicate RUN command for installing numpy and PyTorch 42d9995 abhisheksan commited on Nov 7, 2024
Update Dockerfile to install specific nightly PyTorch version and force reinstall numpy 83c1dd3 abhisheksan commited on Nov 7, 2024
Update Dockerfile to install nightly PyTorch and force reinstall of numpy 23526e0 abhisheksan commited on Nov 7, 2024
Update model name in ModelManager to use Llama-1B-Instruct for improved performance 32aea62 abhisheksan commited on Nov 7, 2024
Enhance ModelManager and PoetryGenerationService with optimizations and new features 6feef58 abhisheksan commited on Nov 7, 2024
Fix initialization check in ModelManager to use class variable for singleton pattern af80dec abhisheksan commited on Nov 6, 2024
Refactor poetry generation to use singleton ModelManager for model and tokenizer initialization 2e998d1 abhisheksan commited on Nov 6, 2024
Set tokenizer's pad token to end-of-sequence token for improved handling 7e19fc6 abhisheksan commited on Nov 6, 2024
Update requirements.txt to upgrade torch to version 2.3.1 ee442da abhisheksan commited on Nov 6, 2024
Update requirements.txt to upgrade transformers and add vllm dependency 5873aa2 abhisheksan commited on Nov 6, 2024
Update Dockerfile to create a cache directory and change application run command port 03d78e4 abhisheksan commited on Nov 6, 2024
Refactor Dockerfile and enhance main.py with Hugging Face integration 2901363 abhisheksan commited on Nov 6, 2024
Add initial project structure with FastAPI and poetry generation service cee4b22 abhisheksan commited on Nov 6, 2024
