Frozen benchmarks, training data, raw eval logs. Code: https://github.com/vignesh19032005/Team_PurpleOps
L PRO
Vignesh19
·
AI & ML interests
None yet
Recent Activity
updated a collection about 15 hours ago
PurpleBench: datasets, benchmarks and eval logs updated a collection about 15 hours ago
PurpleBench: datasets, benchmarks and eval logs updated a collection about 15 hours ago
PurpleBench: datasets, benchmarks and eval logsOrganizations
PurpleBench: datasets, benchmarks and eval logs
Frozen benchmarks, training data, raw eval logs. Code: https://github.com/vignesh19032005/Team_PurpleOps
PurpleBench: models (LoRA adapters for tiny-aya-fire)
LoRA adapters Phase 1-6 + AlignTune retrains (negative results). Recommended: phase4. Code: https://github.com/vignesh19032005/Team_PurpleOps
models 10
Vignesh19/purplebench-tiny-aya-fire-phase5
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase4at2
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase4nd
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase4at
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase6b
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase6
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase4
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase3
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase2
Text Generation • Updated
Vignesh19/purplebench-tiny-aya-fire-phase1
Text Generation • Updated