Production-ready: VRAM-sized batches, frontend API URL fix, repo hygiene

Add temporary /api/debug/gpu to read real VRAM for batch sizing

Symmetric encoder batching: ENC_BATCH cap + chunking + GPU probe

Encoder: use batch word_ids (drop per-sentence re-tokenize); per-model DEC_BATCH + GPU probe

Fix encoder LoRA scaling (read alpha from ckpt); chunk decoder batch

Replace models: new encoder + gemma-3-1b/qwen3 decoders, drop llama3

restrict decoder inference to only emojis

Encoder support for non-word-based languages

UI improvements and HF Spaces preparation

Implemented and deployed encoder + decoder approac