Quantization
التكميم
عملية تحويل القيم المستمرة (مثل أوزان الشبكة العصبية بدقة 32-بت) إلى مجموعة أصغر من المستويات المنفصلة (مثل 4-بت)، مما يُقلِّص حجم التخزين والاستهلاك الذاكري على حساب بعض الدقة.
Mapping continuous values (such as 32-bit neural network weights) to a smaller set of discrete levels (such as 4-bit), reducing storage and memory consumption at the cost of some precision.
Also translated asالتقطيع الرقمي، التكمية، التكميم الرقمي، تقليل دقة التمثيل، خفض دقة المعلمات الرقمية، ضغط النطاق العددي للمصفوفات
First appears in this corpus in: Least Squares Quantization in PCM (1982)
Appears in these papers
- Chronos: Learning the Language of Time Series2024in the sky ✦
- Chronos: Learning the Language of Time Series2024in the sky ✦
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding2016in the sky ✦
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding2016in the sky ✦
- DeepSeek-V3 Technical Report2024in the sky ✦
- DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter2019in the sky ✦
- Billion-Scale Similarity Search with GPUs2017in the sky ✦
- Gemini: A Family of Highly Capable Multimodal Models2023in the sky ✦
- Google's Neural Machine Translation System: Bridging the Gap Between Human and Machine Translation2016in the sky ✦
- Google's Neural Machine Translation System: Bridging the Gap Between Human and Machine Translation2016in the sky ✦
- GPTQ: Accurate Post-Training Quantization for Generative Pre-Trained Transformers2022in the sky ✦
- GPTQ: Accurate Post-Training Quantization for Generative Pre-Trained Transformers2022in the sky ✦
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints2023in the sky ✦
- Jukebox: A Generative Model for Music2020in the sky ✦
- Least Squares Quantization in PCM1982in the sky ✦
- LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale2022in the sky ✦
- LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale2022in the sky ✦
- Mask R-CNN2017in the sky ✦
- Optimal Brain Damage1989in the sky ✦
- QLoRA: Efficient Finetuning of Quantized LLMs2023in the sky ✦
- QLoRA: Efficient Finetuning of Quantized LLMs2023in the sky ✦
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations2020in the sky ✦
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations2020in the sky ✦