Downloads · 30 days
0
beti4/tenacious-judge-simpo-qwen3
tenacious-judge-simpo-qwen3 is a machine learning model from beti4. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: beti4 - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-0.6B
Downloads · 30 days
0
Access
Public
Updated May 2, 2026
Repo size
51.8 MB
Likes
0
Public
Click a slice to open those files.
.safetensors40.4 MB · 78%
From the Hugging Face model README
This qwen3 model was trained 2x faster with Unsloth
This model is a LoRA adapter trained using SimPO (preference optimization) to evaluate B2B outreach quality in Tenacious-style sales workflows.
Evaluated on a sealed held-out Tenacious-Bench set (46 tasks):
Delta A (vs baseline): +0.739 (p < 0.001)
Delta B (vs rule-based): +0.652 (p < 0.001)
Training performed on a single GPU (Colab T4) for ~30–40 minutes.
Apache-2.0