引导式测验 · 中等 等级
模型量化测验
应用量化存储、缩放因子和准确性权衡,包括为什么原始重量减少不能保证完整的模型拟合或速度。
问题 1 的 8
Quantizing a model mainly reduces what?
预览每个问题8 问题
当您参加测验时,就会出现答案和解释。
- Quantizing a model mainly reduces what?
- 用于存储权重和激活的数值精度
- 网络的层数
- 构建模型所依据的训练数据集
- 模型可以理解的语言
- Ignoring scale metadata and other runtime tensors, what is the weight-payload ratio from sixteen bits to four bits per weight?
- The payload is unchanged
- It is one hundredth of the original payload
- The four-bit payload is one quarter of the sixteen-bit payload
- The payload becomes four times larger
- 激进的低位量化的主要缺点是什么?
- 模型忘记了它的训练语言
- 由于值被压缩到更少的桶中,因此可能会损失准确性
- 它只能在超级计算机上运行
- 它会永久删除图层
- 量化感知训练与训练后量化有何不同?
- 它根本不需要任何数据
- 它仅适用于图像
- 它随着时间的推移增加位数
- 它在训练期间模拟舍入,以便模型学会容忍低精度
- 哪种技术使用 4 位量化来在一个 GPU 上实现大型模型的微调?
- 辍学
- 批量归一化
- QLoRA
- 代币化
- 为什么每通道或每组缩放有助于量化模型?
- 它将单独的比例因子分配给权重矩阵的切片以保持精度
- 它消除了对任何重量的需要
- 它使模型更大
- 它将文本转换为音频
- A four-bit model’s raw weights fit in available VRAM, but serving fails out of memory. What could explain this?
- Every four-bit weight expands permanently to a gigabyte
- Quantization guarantees no runtime allocations
- Only the model’s filename consumes the remaining memory
- Caches, scales, unquantized tensors, or workspace need additional memory
- A team quantizes to INT8 but sees no inference speedup. What should it check?
- Whether the training data are alphabetized
- Whether the workload uses efficient supported kernels on its hardware
- Whether lower bit width always guarantees faster execution
- Whether the model must have changed languages