techwithsergiu/Qwen3.5-text-0.8B-bnb-4bit
Text Generation • Updated • 586
Qwen3.5-text-bnb-4bit
Original f16 model → BNB 4-bit quantization → Text-Only BNB 4-bit model for Unsloth LoRA Training
Original f16 model → BNB 4-bit quantization → Text-Only BNB 4-bit model for Unsloth LoRA Training