Pinned Loading

1. fastapi-llm-deployment-service fastapi-llm-deployment-service Public

   High-throughput asynchronous REST API for serving quantized local LLMs

   JavaScript

2. llm-qlora-domain-finetuning llm-qlora-domain-finetuning Public

   Parameter-Efficient Fine-Tuning pipeline for specialized LLMs using 4-bit QLoRA and PEFT.

   Python

3. rag-document-chat-system rag-document-chat-system Public

   Context-aware RAG pipeline using ChromaDB for document retrieval and prompt augmentation.

   JavaScript