Secured / eval

Commit History

Publish final submission package
502016b
verified

gowtham0992 Codex commited on

Add v8 hard eval
325e573
verified

gowtham0992 commited on

Add v7 hard eval
6c03595
verified

gowtham0992 commited on

Sync v8 eval notes
9d4973d
verified

gowtham0992 commited on

Add v8 hard632 report
7d5bd94
verified

gowtham0992 commited on

Publish kitchen table UI
46412d9
verified

gowtham0992 Codex commited on

Promote MiniCPM5 1B LoRA v4
928990e

gowtham0992 Codex commited on

Add v6 hard eval
ac5d69a
verified

gowtham0992 commited on

Add v5 hard eval
0bd3dbe
verified

gowtham0992 commited on

Add MiniCPM5 v2 hard eval
5f2ad89
verified

gowtham0992 commited on

Sync guarded eval runner
9229878
verified

gowtham0992 Codex commited on

Ship MiniCPM LoRA v3
cc862d5

gowtham0992 Codex commited on

Add sanitized field scam examples
113d9bf

gowtham0992 Codex commited on

Document honest submission guardrails
d729e70

gowtham0992 Codex commited on

Add Jawbreaker training and fallback spine
6fa99e6

gowtham0992 Codex commited on

Pivot runtime to OpenBMB MiniCPM
9b17df4

gowtham0992 Codex commited on

Document final runtime and submission state
9c5ce62

gowtham0992 Codex commited on

Wire app to configurable model backend
8c85b65

gowtham0992 Codex commited on

Add model bakeoff evaluation harness
5971541

gowtham0992 Codex commited on

Build 100-case scam eval spine
292a298

gowtham0992 Codex commited on

Initialize Jawbreaker hackathon scaffold
6103e1f

gowtham0992 commited on