Modelpublic

ChesterProgrammer/Test-2

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes5downloads

Model Card

Method Lora(16 bit) Epochs 2 Batch size 4 Grad Accum 1 Learning rate 0.0002 Optimizer AdamW 8-bit Context length 2048 Warmup steps 2 Packing False weight decay 0.001 seed 3407

LoRA Rank 8 Alpha 16 Dropout 0.05 Variant lora

Uploaded finetuned model

—Developed by: ChesterProgrammer
—License: apache-2.0
—Finetuned from model : DreamFast/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark

This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.