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
updated a model 13 days ago
AZERDSQ/G0-nano-instruct updated a model 13 days ago
AZERDSQ/G0-nano-base liked a model 13 days ago
AZERDSQ/G2-nano-safetyOrganizations
None yet
models 7
AZERDSQ/G0-nano-instruct
Text Generation • 62.1M • Updated • 627 • 6
AZERDSQ/G0-nano-base
Text Generation • 62.1M • Updated • 598 • 1
AZERDSQ/G2-nano-safety
Text Classification • 60M • Updated • 59 • 3
AZERDSQ/G2-nano-instruct
Text Generation • 60M • Updated • 317 • 1
AZERDSQ/G2-nano-base
Text Generation • 60M • Updated • 312 • 1
AZERDSQ/G1-nano-base
Text Generation • 60M • Updated • 56 • 1
AZERDSQ/G1-nano-instruct
Text Generation • 60M • Updated • 82 • 2
datasets 0
None public yet