piyawudk/PhishMe-12k-Qwen3.5-4B-GSPO-v2
011
Uploaded finetuned model
- Developed by: piyawudk
- License: apache-2.0
- Finetuned from model : piyawudk/PhishMe-12k-Qwen3.5-4B-CS-FFT-v3
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.
