From b6fbfac2ae256309ba861d692c50a1096f253cb1 Mon Sep 17 00:00:00 2001 From: Mortdecai Date: Sat, 21 Mar 2026 15:31:39 -0400 Subject: [PATCH] Add README with training progress chart and bake-off results Co-Authored-By: Claude Opus 4.6 (1M context) --- README.md | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 README.md diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae1fc65 --- /dev/null +++ b/README.md @@ -0,0 +1,62 @@ +# Mortdecai + +A 9B parameter language model fine-tuned for Minecraft server operations. Translates natural language to commands, controls an AI God character, manages plugins, writes mcfunction scripts, and learns from its mistakes. + +**Base model:** Qwen3.5-9B | **Current version:** 0.5.0 | **Quantization:** Q4_K_M (5.6GB) + +## Training Progress + +![Training Progress](branding/training_progress.svg) + +## Bake-off: 0.5.0 vs 0.4.0 + +| Category | 0.4.0 | 0.5.0 | Change | +|----------|-------|-------|--------| +| Enchantments | 20% | 67% | **+47%** | +| EssentialsX | 0% | 60% | **+60%** | +| Effects | 0% | 25% | **+25%** | +| Basic commands | 75% | 75% | — | +| Teleport | 100% | 100% | — | +| Overall | 45.2% | 46.8% | +1.6% | + +## Architecture + +**17 tools** across 5 categories: + +| Category | Tools | +|----------|-------| +| Execution | `rcon.execute` | +| Knowledge | `minecraft.wiki_lookup`, `plugin.docs_lookup`, `minecraft.changelog_lookup`, `paper.docs_lookup` | +| World | `world.player_info`, `world.server_state`, `world.nearby_entities` | +| Memory | `memory.read`, `memory.write` | +| Scripts | `script.write`, `script.validate`, `script.execute`, `script.read`, `script.list`, `script.delete`, `script.schedule` | + +**Plugins:** FastAsyncWorldEdit, WorldGuard, CoreProtect, EssentialsX, Vault, LuckPerms + +## Training Data + +~20,000+ examples from: +- Hand-curated seed data (3,196) +- Tool-calling sequences with 17 tools (1,430) +- IGLU build dataset — Microsoft Research (4,656) +- RCON-validated plugin examples (104) +- Exploration self-play with wiki grounding (150) +- Self-play across 3 GPUs (2,900+) +- Live server audit from wolf bots + real players (8,000+) + +## Infrastructure + +| GPU | Role | +|-----|------| +| RTX 3090 Ti (24GB) | Training + self-play | +| RTX 2080 Ti (11GB) | Exploration self-play | +| Quadro RTX 4000 (8GB) | Production inference — 3 MC servers | +| GTX 1660 Super (6GB) | Prompt generation | + +**GPU Scheduler:** [gpu.sethpc.xyz](https://gpu.sethpc.xyz) — preset-based job scheduler with live monitoring + +## Links + +- **Play:** `minecraft.mortdec.ai` +- **Model card:** [MODEL_CARD.md](MODEL_CARD.md) +- **Domain:** [mortdec.ai](https://mortdec.ai)