Update README: add achievement/track/sponsor tags, expand story section

Fix broken relative links in README and FIELD_NOTES

Final hackathon submission: README, Field Notes, UI overhaul, fine-tuned model

Reproducción inline de canciones y cuentos, mic como botón de terminar

Add real song playback, precache stories, improve LLM fallback

Stop tracking CLAUDE.md/PLAN.md in the Space repo

Add panel parental, fix app.py docstring, model card, and open trace

Add QLoRA fine-tune pipeline (mérito 2, Well-Tuned)

Add Sofia color-change, Cuentos frontend section, Ollama local backend

Remove internal hackathon notes and dead prototypes from the repo

Rework frontend UI, add Actividades and Canciones sections

Tune ZeroGPU queue duration; document per-visitor daily quota

Simplify startup flow: drop scripted greeting, start from child's first turn

Clean up stale GGUF/llama.cpp references in PLAN.md and finetune/README.md

Document verified ZeroGPU pivot + gotchas

Fix ZeroGPU import order: spaces before torch

Add retry + curated-content fallback for ZeroGPU allocation failures

Fix ZeroGPU startup crash: force Kokoro TTS onto CPU

Pivot LLM runtime: llama.cpp (CPU) -> transformers + ZeroGPU

Revert "Switch llama-cpp-python to CUDA wheel for T4-small upgrade"

Switch llama-cpp-python to CUDA wheel for T4-small upgrade

Fix LLM perf on free CPU tier: pin n_threads=2, warmup at startup

Use prebuilt CPU wheel for llama-cpp-python

Pin Space to Python 3.12 (matches the env we validated locally)

Match Space's provisioned gradio/python versions in frontmatter

Merge Space template (.gitattributes), keep our README/app

Rename persona Lumi -> Sofía, prep for HF Space deploy

initial commit

Initial commit: Lumi pipeline migrated to llama.cpp, local-first TTS