Seth/Mortdecai
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update PLAN.md with bake-off decisions and hardware assignments

Browse Source 
Key decisions: gemma3n:e4b for serving (RTX 4000), qwen3:8b for
fine-tuning base (RTX 3090 Ti). Phase 1 complete.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Seth Freiberg
2026-03-18 10:41:47 -04:00
parent 48b627d498
commit eaa9e0c26b
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
PLAN.md
+5 -1
View File
@@ -319,7 +319,11 @@ These are ideas to explore after the core system is working. Prioritize based on
| Date | Decision | Rationale |
|------|----------|-----------|
| 2026-03-18 | Base model: `qwen3-coder` | Good code/instruction following, runs on homelab hardware via Ollama, LoRA-friendly |
| 2026-03-18 | ~~Base model: `qwen3-coder`~~ | ~~Good code/instruction following~~ — **Superseded: see below** |
| 2026-03-18 | Serving model: `gemma3n:e4b` (6.9B) | Bake-off winner: 80.6% cmd match, 100% safety, 5.9s latency. Beats qwen3-coder:30b on all metrics. Deployed to RTX 4000 on node-197. |
| 2026-03-18 | Fine-tuning base: `qwen3:8b` (dense, Apache 2.0) | 77.4% cmd match with token budget fix. Best syntax quality, perfect safety, strong Unsloth ecosystem. Token-budget issue = exactly what LoRA fixes. |
| 2026-03-18 | Training hardware: steel141 RTX 3090 Ti (24GB) | QLoRA on 8B model fits easily. Conda env `mc-train` with Unsloth 2026.3.5 ready. |
| 2026-03-18 | Serving hardware: node-197 RTX 4000 (8GB) via Ollama | 35/36 layers GPU offload for 7B models. Always-on, no desktop contention. |
| 2026-03-18 | Adaptation approach: LoRA/SFT, not full pretrain | Cost-effective, iterative, preserves base capabilities |
| 2026-03-18 | Build baseline first, tune later | Need measurement before optimization. Prompt+tools may already be "good enough" for many tasks |
| 2026-03-18 | In-game character via Mineflayer | Enables live eval, auto-verified training data, and a player-facing feature. Mineflayer supports 1.21.x |