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
published a model about 3 hours ago
tomhu/Qwen3-Coder-Next-SWE-Prune-26B-A3B-Rebench-GRPO updated a model about 3 hours ago
tomhu/Qwen3-Coder-Next-SWE-Prune-GATE-70 updated a model about 3 hours ago
tomhu/Qwen3-Coder-Next-SWE-Prune-REAP-70Organizations
None yet
models 49
tomhu/Qwen3-Coder-Next-SWE-Prune-26B-A3B-Rebench-GRPO
Updated
tomhu/Qwen3-Coder-Next-SWE-Prune-GATE-70
Text Generation • 26B • Updated
tomhu/Qwen3-Coder-Next-SWE-Prune-REAP-70
Text Generation • 26B • Updated
tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70
Text Generation • 26B • Updated
tomhu/RL4TG-Qwen3-8B-Offline-SFT-GRPO
Text Generation • 8B • Updated • 18
tomhu/RL4TG-Qwen3-8B-OPD-GRPO
Text Generation • 8B • Updated • 19
tomhu/RL4TG-Qwen3-8B-Direct-GRPO
Text Generation • 8B • Updated • 22
tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO
Text Generation • 1B • Updated • 34
tomhu/RL4TG-DeepSeek-Coder-1.3B-GRPO
Text Generation • 1B • Updated • 39
tomhu/RL4TG-DeepSeek-Coder-1.3B-OPD6.7B-GRPO
Text Generation • 1B • Updated • 31