admin/modelTesting
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 2f99dd1e35 Grade muse-glimmer-28b full 7-prompt battery — new benchmark leader main AygeaandClaude 2026-08-10 13:13:54 -07:00
  • 3507d33006 Grade 12-model backlog + fix native-API TTFT capture AygeaandClaude 2026-07-28 21:17:08 -07:00
  • 8806c88a71 Handoff: capture workflow in CLAUDE.md + per-session memory files adminandClaude 2026-07-28 20:33:21 -07:00
  • c98b6bb257 Capture uncensored-Qwen-35B automation (others hung via API) adminandClaude 2026-07-28 20:21:13 -07:00
  • 0c79a997f5 Capture kat-coder + qwen3-coder-30b outputs (5 prompts each, API-run, NOT graded yet) adminandClaude 2026-07-28 19:22:41 -07:00
  • b9f45a7c46 Gemma 4 26B-A4B head-to-head vs Qwen (4 prompts, via grade_run.py API) adminandClaude 2026-07-28 18:42:58 -07:00
  • b82c665ec6 Add tools/grade_run.py: call LM Studio API, save output + capture metrics adminandClaude 2026-07-28 18:16:00 -07:00
  • 241298b410 Grade Qwen 6-bit on webhook prompt: 75/100 Minor Flaws (runs, all 4 tests pass) adminandClaude 2026-07-28 18:03:50 -07:00
  • e3d73de36a Grade Qwen 6-bit on Rust prompt: 50/100 Critical (does not compile, 7 errors) adminandClaude 2026-07-28 17:53:15 -07:00
  • dd5724ed77 First multi-prompt result: Qwen 6-bit TTS = 49 (vs 82 LFU) + per-prompt schema adminandClaude 2026-07-28 17:43:38 -07:00
  • e3e5fded6d Add Cloud-Offload Strategy panel (local backup for cloud credits) adminandClaude 2026-07-28 17:20:27 -07:00
  • ec6fd7157a Add Aygea Test prompt battery: 6 prompts from real project shapes adminandClaude 2026-07-28 17:16:03 -07:00
  • de748f4854 Add Key Findings panel + Aygea Test prompt battery adminandClaude 2026-07-28 17:12:56 -07:00
  • 8d2d5cd562 Grade 3 more models + dashboard v2 layout (quant/format as first-class) adminandClaude 2026-07-28 16:51:50 -07:00
  • 4056470a46 Docs: record docker-compose + webhook deploy architecture in CLAUDE.md adminandClaude 2026-07-28 14:29:17 -07:00
  • a93fe6f15e Add Authorization-header + /hook proxy to webhook/deploy adminandClaude 2026-07-28 14:28:16 -07:00
  • b97658e067 Add Gitea-push webhook for auto-deploy adminandClaude 2026-07-28 14:20:03 -07:00
  • 42291f61b8 Switch host port to 31415 (obscure; keep low ports free) adminandClaude 2026-07-28 14:13:04 -07:00
  • 7db45049dc Add docker-compose + deploy.sh (Coolify replacement) adminandClaude 2026-07-28 14:11:47 -07:00
  • 8da63db701 Docs: CLAUDE.md deploy notes, README, DEPLOY.md, Dockerfile adminandClaude 2026-07-28 14:01:43 -07:00
  • f0281f2878 Initial benchmark suite: 8 graded models + cyberpunk dashboard generator adminandClaude 2026-07-28 14:00:40 -07:00