Gleam Lab · Tag Archive
Tag: QLoRA
2 articles collected by topic for tutorials, cases, engineering practice, and research notes.
AI Research 42 - Multimodal Large Model Quantization: From FP32 to INT4, the Final Summary
Survey outline for multimodal large model quantization schemes: from FP32 to INT4. Core goal is model capability retention, compression efficiency 50-75%...
AI Research 39 - Multimodal Large Model Quantization: How Fine-Tuning and Quantization Maximize Performance
In multimodal large model optimization, the order choice of fine-tuning and quantization directly affects the final model's performance and efficiency.