---
title: Oneiros
emoji: 🌙
colorFrom: purple
colorTo: indigo
sdk: gradio
sdk_version: "4.40.0"
python_version: "3.10"
app_file: app.py
pinned: true
short_description: Map your dreams with a small model — no ChatGPT API.
preload_from_hub:
  - repo_id: Qwen/Qwen2.5-7B-Instruct-GGUF
    filename: qwen2.5-7b-instruct-q4_k_m-00001-of-00002.gguf
  - repo_id: Qwen/Qwen2.5-7B-Instruct-GGUF
    filename: qwen2.5-7b-instruct-q4_k_m-00002-of-00002.gguf
startup_duration_timeout: 45m
# rebuild: cc5f140 force fresh build 2026-06-03
---

# ✦ ONEIROS

**Your dreams, mapped with a small model you control — not sent to ChatGPT.**

Oneiros mengubah catatan mimpi menjadi **peta SVG** plus panel ringkasan entitas, menggunakan **Qwen2.5-7B-Instruct** (GGUF) via **llama-cpp-python** — tanpa API LLM pihak ketiga.

Proyek ini dibuat untuk [Build Small Hackathon](https://huggingface.co/build-small-hackathon) (Gradio × Hugging Face), track **An Adventure in Thousand Token Wood**.

---

## Status repositori (Day 1)

| Komponen | Status |
|----------|--------|
| `model/` loader + extractor + normalisasi | ✅ Day 1 |
| `app.py` minimal (mimpi → JSON) | ✅ Day 1 |
| `storage/trace_logger.py` | ✅ Day 1 |
| `tests/test_extractor.py` | ✅ (butuh GGUF lokal) |
| Peta SVG (`map/`) | 🔲 Day 2 |

---

## Deploy HF Space

**Space resmi:** https://huggingface.co/spaces/build-small-hackathon/oneiros

1. Sebelum push: `./scripts/prepare_space_requirements.sh` (salin wheel Linux ke `requirements.txt`).
2. Push ke org `build-small-hackathon/oneiros`.
3. **Variables** (Settings): `N_GPU_LAYERS=0`, `N_CTX=4096`; `ONEIROS_SKIP_WARMUP=1` sampai preload selesai.
4. Preload 2 shard Q4_K_M (~15–45 menit). Cek log: `[oneiros] diagnosis` → `shard_pair_ok: True`.
5. Setelah Running: uji 1 mimpi di UI.

Detail: [docs/08-deploy-hf-space.md](docs/08-deploy-hf-space.md) · Checklist Day 2: [docs/16-checklist-sebelum-day2.md](docs/16-checklist-sebelum-day2.md).

---

## Quick start (lokal)

**Pakai `requirements-local.txt`** — jangan `requirements.txt` (itu untuk Space Linux).

```bash
python -m venv .venv && source .venv/bin/activate
pip install -r requirements-local.txt

# Model — opsi cepat (Q2_K ~3GB) atau Q4_K_M (2 shard)
hf download Qwen/Qwen2.5-7B-Instruct-GGUF qwen2.5-7b-instruct-q2_k.gguf --local-dir ./models

# Atau Q4_K_M (kualitas lebih baik):
# hf download Qwen/Qwen2.5-7B-Instruct-GGUF \
#   qwen2.5-7b-instruct-q4_k_m-00001-of-00002.gguf \
#   qwen2.5-7b-instruct-q4_k_m-00002-of-00002.gguf \
#   --local-dir ./models

CMAKE_ARGS="-DGGML_METAL=on" pip install llama-cpp-python --force-reinstall --no-cache-dir

python scripts/verify_day1.py
python scripts/smoke_model.py
python tests/test_extractor.py
python scripts/run_mimpi_uji.py
python app.py
```

---

## Day 1 — perintah verifikasi

| Perintah | DoD |
|----------|-----|
| `python scripts/smoke_model.py` | Model load + 1 respons |
| `python tests/test_extractor.py` | 3/3 test cases |
| `python scripts/run_mimpi_uji.py` | ≥8/10 parse OK → `tests/results/mimpi_uji_log.json` |
| Space Running | JSON dari 1 mimpi contoh di UI |

---

## Dokumentasi

| Dokumen | Isi |
|---------|-----|
| [Indeks dokumentasi](docs/README.md) | Peta lengkap |
| [Setup lokal](docs/07-setup-lokal.md) | Mac / Metal |
| [Timeline](docs/13-timeline-hackathon.md) | Day 0–5 |

**Konteks Cursor:** [`ONEIROS_CURSOR_CONTEXT.md`](ONEIROS_CURSOR_CONTEXT.md).

---

## Lisensi

TBD — tentukan sebelum publish ke Hub.

---

*Build Small Hackathon 2026 · Oneiros*