FINAL-Bench
/

Darwin-2B-Opus-LoRA

Model card Files Files and versions

Darwin-2B-Opus-LoRA (PRIVATE)

Darwin V8 LoRA adapter for Darwin-2B-Opus.

Base: Qwen/Qwen3.5-2B
Rank: 16, alpha: 32, target: all-linear
Training: 9,762 samples (Opus/Sonnet/Korean reasoning), 29 min on 8xB200
Use merged version: FINAL-Bench/Darwin-2B-Opus

This model is introduced in Darwin Family.

Downloads last month: 31

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for FINAL-Bench/Darwin-2B-Opus-LoRA

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Adapter

(77)

this model

Collection including FINAL-Bench/Darwin-2B-Opus-LoRA

DARWIN-Family

비드래프트 • 49 items • Updated about 11 hours ago • 18

Paper for FINAL-Bench/Darwin-2B-Opus-LoRA

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning

Paper • 2605.14386 • Published 4 days ago • 50

Article mentioning FINAL-Bench/Darwin-2B-Opus-LoRA

"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"