Qwengram augments frozen Qwen backbones with transferred Qwen3.8 Flash-Next n-gram memory using a small trained reader and dynamic gate.
Nicolo' D'Evangelista
Ninnix96
AI & ML interests
None yet
Recent Activity
new activity about 6 hours ago
Ninnix96/Qwengram-4B:Very interesting, Qwen3.8 27B when? updated a model about 6 hours ago
Ninnix96/Qwengram-4B updated a model about 6 hours ago
Ninnix96/Qwengram-2BOrganizations
None yet
models 5
Ninnix96/Qwengram-4B
Text Generation • 4B • Updated • 220 • 2
Ninnix96/Qwengram-2B
Text Generation • 2B • Updated • 556 • 2
Ninnix96/Qwengram-0.8B
Text Generation • 0.8B • Updated • 2.09k • 11
Ninnix96/KAT-Coder-V2.5-Dev-gguf
Text Generation • 35B • Updated • 83 • 1
Ninnix96/Qwen3.6-35B-A3B-gguf
Text Generation • 35B • Updated • 392 • 2
datasets 0
None public yet