Sync model card from docs/model_cards/qwen14b-code-trainer-v7_mixed.md

V7 agent eval (nexus-aligned): 5/5 making progress

V7 tool-calling eval (nexus-aligned): 7/10 (70%)

V7 agent eval: 5/5 making progress

V7 tool-calling eval: 3/10 (30%)

Phase 4 benchmark: gsm8k (0-shot)

Phase 4 eval-only: phase4-eval-v7.json

Phase 4 eval-only: phase4-eval-v7.json

Phase 4A v7_mixed sweep — eval_loss=0.35945001244544983

initial commit