admin
0 Followers · 0 Following
Joined on 2026-01-20
Repositories
4
 Projects Packages Public Activity Starred Repositories
admin pushed to main at admin/mcode-sl 2026-10-19 23:28:09 -07:00
7614392ef3 docs: record rollout acceptance on all machines (2x ubuntu, macOS, TUI render)
admin pushed to main at admin/mcode-sl 2026-10-19 23:25:23 -07:00
fd8e8cbbd7 docs: AGENTS.md + evidence-backed scaffold (state, trials, decisions, handoff)
admin created branch main in admin/mcode-sl 2026-10-19 23:16:42 -07:00
admin pushed to main at admin/mcode-sl 2026-10-19 23:16:42 -07:00
9ad073d4fc first commit
admin created repository admin/mcode-sl 2026-10-19 21:41:33 -07:00
admin pushed to main at admin/modelTesting 2026-08-10 13:13:56 -07:00
2f99dd1e35 Grade muse-glimmer-28b full 7-prompt battery — new benchmark leader
admin pushed to main at admin/modelTesting 2026-07-28 21:17:18 -07:00
3507d33006 Grade 12-model backlog + fix native-API TTFT capture
admin pushed to main at admin/modelTesting 2026-07-28 20:33:24 -07:00
8806c88a71 Handoff: capture workflow in CLAUDE.md + per-session memory files
admin pushed to main at admin/modelTesting 2026-07-28 20:21:16 -07:00
c98b6bb257 Capture uncensored-Qwen-35B automation (others hung via API)
admin pushed to main at admin/modelTesting 2026-07-28 19:22:44 -07:00
0c79a997f5 Capture kat-coder + qwen3-coder-30b outputs (5 prompts each, API-run, NOT graded yet)
admin pushed to main at admin/modelTesting 2026-07-28 18:43:00 -07:00
b9f45a7c46 Gemma 4 26B-A4B head-to-head vs Qwen (4 prompts, via grade_run.py API)
admin pushed to main at admin/modelTesting 2026-07-28 18:16:03 -07:00
b82c665ec6 Add tools/grade_run.py: call LM Studio API, save output + capture metrics
admin pushed to main at admin/modelTesting 2026-07-28 18:03:53 -07:00
241298b410 Grade Qwen 6-bit on webhook prompt: 75/100 Minor Flaws (runs, all 4 tests pass)
admin pushed to main at admin/modelTesting 2026-07-28 17:53:18 -07:00
e3d73de36a Grade Qwen 6-bit on Rust prompt: 50/100 Critical (does not compile, 7 errors)
admin pushed to main at admin/modelTesting 2026-07-28 17:43:41 -07:00
dd5724ed77 First multi-prompt result: Qwen 6-bit TTS = 49 (vs 82 LFU) + per-prompt schema
admin pushed to main at admin/modelTesting 2026-07-28 17:20:29 -07:00
e3e5fded6d Add Cloud-Offload Strategy panel (local backup for cloud credits)
admin pushed to main at admin/modelTesting 2026-07-28 17:16:04 -07:00
ec6fd7157a Add Aygea Test prompt battery: 6 prompts from real project shapes
admin pushed to main at admin/modelTesting 2026-07-28 17:12:58 -07:00
de748f4854 Add Key Findings panel + Aygea Test prompt battery
admin pushed to main at admin/modelTesting 2026-07-28 16:51:53 -07:00
8d2d5cd562 Grade 3 more models + dashboard v2 layout (quant/format as first-class)
admin pushed to main at admin/modelTesting 2026-07-28 14:29:19 -07:00
4056470a46 Docs: record docker-compose + webhook deploy architecture in CLAUDE.md