Sub-3-bit Qwen3 recovered with quantization-aware distillation then on-policy distillation. -QAD entries are training starting points.
Chen Yuan
MingZwhy
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
QAOPD updated a collection 1 day ago
QAOPD updated a collection 1 day ago
QAOPDOrganizations
models 13
MingZwhy/Qwen3-4B-W1.88-QAD
Text Generation • 196k • Updated • 129
MingZwhy/Qwen3-4B-W2.79-QAD
Text Generation • 196k • Updated • 130
MingZwhy/Qwen3-1.7B-W1.88-QAD
Text Generation • 2B • Updated • 130
MingZwhy/Qwen3-1.7B-W2.79-QAD
Text Generation • 2B • Updated • 132
MingZwhy/Qwen3-0.6B-W1.88-QAD
Text Generation • 0.6B • Updated • 262
MingZwhy/Qwen3-0.6B-W2.79-QAD
Text Generation • 0.6B • Updated • 261
MingZwhy/Qwen3-4B-W1.88-QAOPD
Text Generation • 4B • Updated • 242
MingZwhy/Qwen3-4B-W2.79-QAOPD
Text Generation • 4B • Updated • 222
MingZwhy/Qwen3-1.7B-W1.88-QAOPD
Text Generation • 2B • Updated • 200
MingZwhy/Qwen3-1.7B-W2.79-QAOPD
Text Generation • 2B • Updated • 189
datasets 0
None public yet