Commit Graph

4 Commits

Author SHA1 Message Date
Seth 06b082bd21 0.5.0 pre-training: 9,444 examples, prod pattern fixes
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 21:48:54 -04:00
Seth 7a31e500e4 Qwen3.5-9B on prod, Gemini 2.5 Flash for dev, error correction, branding
Prod deployment:
- paper-ai and shrink-world switched from gemma3n:e4b to qwen3.5:9b
- Error correction: detects RCON errors (<--[HERE]), asks model to fix, retries
- Broadened error patterns: Unknown game mode, Unknown enchantment, etc.
- Fixed fire fallback matching "firework" as fire intent
- Fixed command format examples (WRONG vs RIGHT in prompt)
- max_tokens bumped to 600 for command calls
- Removed template workflow commands from sudo prompt

Dev server:
- Gemini 2.5 Flash ($0.15/$0.60 per M tokens) replaces Flash Lite
- 10 bots for ~$1-1.5/hr training data generation
- Dynamic pricing by model name in cost tracker

Branding:
- Rajdhani Bold as official Mortdecai font
- Logo variants: mortdecai + mortdec.ai in 6 fonts
- Whitelist page updated with Mortdecai branding + mortdec.ai domain

Whitelist UUID fix:
- Looks up real Mojang UUID via api.mojang.com
- Patches all whitelist.json files directly
- No more offline-mode UUID mismatches

WorldEdit schematics:
- 77 schematics installed (villages, bridges, lighthouses, parks, etc.)

Mortdecai v4 training in progress: 63% complete on steel141

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 23:09:27 -04:00
Seth e780aef8c6 v3 model trained (1,308 examples, loss 0.55), API cascade, context update
v3 training:
- 1,308 examples: curated + Claude-distilled + bot audit + recipes + command ref
- 1 epoch, rank 16, LR 1e-4, loss 0.55 (sweet spot)
- GGUF Q4_K_M exported, loaded in Ollama as qwen3-8b-mc-lora-v3
- Correct commands, no Chinese, proper safety refusals, dramatic God persona

API cascade for dev server:
- Stage 1: Claude Haiku ($20 budget, ~$11 spent)
- Stage 2: Gemini 2.5 Flash Lite ($20 budget)
- Stage 3: qwen3-8b-mc-lora-v3 (free, local)
- Gemini call function with persistent cost tracking
- Full status report printed at each $1 milestone

Data collection: 2,677 dev audit entries and growing
Bot status printer budget display fix

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 04:52:04 -04:00
Seth 0473eb0b50 Minecraft knowledge corpus, recipe trees, GitHub scraper, 644 examples
Knowledge corpus (knowledge/mc-data/):
- 1505 items, 886 crafting recipes, 1166 blocks from minecraft-data 1.21.11
- Recipe dependency tree builder (knowledge/build_recipe_tree.py)
- Crafting chain training: "give me everything to make X from scratch"
- Smelting recipes, version awareness examples

Training data (644 examples total):
- 107 command syntax reference examples (every command + common errors)
- 176 recipe/crafting chain examples (63 crafting, 103 material-giving, 11 smelting)
- 344 Claude-distilled examples (222 sudo + 122 god via Haiku)
- Live bot audit data ingested (128 examples from dev server)

Swarm bots:
- Swimming/water escape logic
- Door opening
- Context-aware prayers (inventory, health, time, depth)
- Prefix enforcement on all Gemini/Dolphin prompts

GitHub log scraper (data/scrape_server_logs.py):
- Searches GitHub for Minecraft server logs with commands
- Strict 1.20.5+ version filter
- Extracts command pairs, converts to training format

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 20:33:09 -04:00