QuantumStackOverflow/ASTER_4B_RL
Reinforcement Learning • 4B • Updated • 136 • 1
GlitchNova
QuantumStackOverflow
AI & ML interests
None yet
Recent Activity
liked a model about 4 hours ago
QuantumStackOverflow/ASTER_4B_RL upvoted a paper 18 days ago
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding upvoted a paper about 2 months ago
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training StepsOrganizations
None yet
liked a
model about 4 hours ago