Qwen3-Coder-Next MoE models pruned for software engineering using REAP, gate-based, and activation-based expert importance.
tomsawyer
tomhu
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents updated a model about 19 hours ago
tomhu/Qwen3-Coder-Next-SWE-Prune-26B-A3B-Rebench-OPD published a model about 23 hours ago
tomhu/Qwen3-Coder-Next-SWE-Prune-26B-A3B-Rebench-OPDOrganizations
None yet
models 50
tomhu/Qwen3-Coder-Next-SWE-Prune-26B-A3B-Rebench-OPD
Updated
tomhu/Qwen3-Coder-Next-SWE-Prune-26B-A3B-Rebench-GRPO
Updated • 14
tomhu/Qwen3-Coder-Next-SWE-Prune-GATE-70
Text Generation • 26B • Updated • 260
tomhu/Qwen3-Coder-Next-SWE-Prune-REAP-70
Text Generation • 26B • Updated • 161
tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70
Text Generation • 26B • Updated • 164
tomhu/RL4TG-Qwen3-8B-Offline-SFT-GRPO
Text Generation • 8B • Updated • 4
tomhu/RL4TG-Qwen3-8B-OPD-GRPO
Text Generation • 8B • Updated • 5
tomhu/RL4TG-Qwen3-8B-Direct-GRPO
Text Generation • 8B • Updated • 6
tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO
Text Generation • 1B • Updated • 7
tomhu/RL4TG-DeepSeek-Coder-1.3B-GRPO
Text Generation • 1B • Updated • 9