Same ~60M shape as G1-nano, trained from scratch on 2× tokens (3B). Weak gains, likely a 60M ceiling. Base + instruct — lab note, not a G1 upgrade.
Jules YZERD
AZERDSQ
AI & ML interests
None yet
Recent Activity
liked a dataset 8 days ago
WithinUsAI/claude_mythos_distilled_25k updated a model 27 days ago
AZERDSQ/G0-nano-instruct updated a model 27 days ago
AZERDSQ/G0-nano-baseOrganizations
None yet
models 7
AZERDSQ/G0-nano-instruct
Text Generation • 62.1M • Updated • 635 • 6
AZERDSQ/G0-nano-base
Text Generation • 62.1M • Updated • 621 • 1
AZERDSQ/G2-nano-safety
Text Classification • 60M • Updated • 110 • 3
AZERDSQ/G2-nano-instruct
Text Generation • 60M • Updated • 365 • 1
AZERDSQ/G2-nano-base
Text Generation • 60M • Updated • 358 • 1
AZERDSQ/G1-nano-base
Text Generation • 60M • Updated • 29 • 1
AZERDSQ/G1-nano-instruct
Text Generation • 60M • Updated • 42 • 2
datasets 0
None public yet