From cc86a97d10403b4983d3ddcdc6664af5b3bc1291 Mon Sep 17 00:00:00 2001 From: marcuspaico Date: Sat, 15 Aug 2026 14:25:27 -0700 Subject: [PATCH] docs: record verified tilde-alias model ID in constraints Co-Authored-By: Claude Fable 5 --- docs/superpowers/plans/2026-08-14-buddha-gpt.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/superpowers/plans/2026-08-14-buddha-gpt.md b/docs/superpowers/plans/2026-08-14-buddha-gpt.md index 76c702c..7834341 100644 --- a/docs/superpowers/plans/2026-08-14-buddha-gpt.md +++ b/docs/superpowers/plans/2026-08-14-buddha-gpt.md @@ -14,7 +14,7 @@ - Training runs ONLY on local Apple M5, 24 GB — `mlx_lm.lora` with 4-bit base; no GPU rental. - All API calls go through OpenRouter (OpenAI-compatible, base_url `https://openrouter.ai/api/v1`), key from env `OPENROUTER_API_KEY` or file `.openrouter_key` (gitignored). Budget ceiling: $100; expected ~$6. Log token usage from every response. -- Model roles (exact OpenRouter IDs): data gen `deepseek/deepseek-v4-flash-latest`; judge `google/gemini-flash-latest`; frontier reference system `moonshotai/kimi-k3`; judge-agreement check `deepseek/deepseek-v4-pro`. The judge must never be one of the compared systems. +- Model roles (exact OpenRouter IDs): data gen `~deepseek/deepseek-v4-flash-latest` (OpenRouter's catalog ID for the latest-alias — tilde prefix is part of the real ID); judge `google/gemini-flash-latest`; frontier reference system `moonshotai/kimi-k3`; judge-agreement check `deepseek/deepseek-v4-pro`. The judge must never be one of the compared systems. - Base model: `mlx-community/Qwen2.5-7B-Instruct-4bit` (Apache-2.0). Do not substitute a non-Apache model. - Corpus licensing: only CC0/CC-BY/public-domain texts enter training data or the repo. - Eval prompts (Tasks 7–9) are hold-out: never used in data generation or training.