Downloads · 30 days
13
26% of all-time downloads
Darwin-Chimera-4B-MoE-2E-PoC
FINAL-Bench/Darwin-Chimera-4B-MoE-2E-PoC
Darwin-Chimera-4B-MoE-2E-PoC is a text generation model from FINAL-Bench. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
2-expert MoE upcycling PoC: Qwen3.5-4B (expert0) + Reasoning-Fix (expert1), fused as one Qwen3.5-MoE with a trained router (frozen experts).
All-time downloads
50
Public
Parameters
8.7B
17.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.5 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- qwen3_5_moe_text
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026
- SHA
- 0cf6f4e0
Try a prompt
Model card
From the Hugging Face model README
Darwin-Chimera-4B-MoE-2E-PoC (private)
2-expert MoE upcycling PoC: Qwen3.5-4B (expert0) + Reasoning-Fix (expert1), fused as one Qwen3.5-MoE with a trained router (frozen experts).
What it proves
- Two parents' FFNs preserved 100% as frozen experts (trace intact, single-parent non-reducible).
- Router trained (163K params) → both experts genuinely used (~49-56%), coherent generation.
- Honest result: neutral vs base on accuracy (parents too similar) — this is a mechanism/originality PoC, not a performance model. Real gains come from divergent parents + RFT-edge (see Darwin-V9-Chimera-4B-RFT).
Build/verify scripts: chimera_build.py / chimera_router_train.py / chimera_verify.py.
- Task
- Text Generation
- Type
- qwen3_5_moe_text
- License
- apache-2.0
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026