From 712db785690c92524a35036d4f00a53d4138061a Mon Sep 17 00:00:00 2001 From: skindhu Date: Tue, 5 Nov 2024 17:16:45 +0800 Subject: [PATCH] add fourth chapter --- ....从零开始实现一个用于文本生成的 GPT 模型.md | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/cn-Book/4.从零开始实现一个用于文本生成的 GPT 模型.md b/cn-Book/4.从零开始实现一个用于文本生成的 GPT 模型.md index 3ab121a..4540fb9 100644 --- a/cn-Book/4.从零开始实现一个用于文本生成的 GPT 模型.md +++ b/cn-Book/4.从零开始实现一个用于文本生成的 GPT 模型.md @@ -159,7 +159,7 @@ print(batch) ```python tensor([[ 6109, 3626, 6100, 345], #A - [ 6109, 1110, 6622, 257]]) + [ 6109, 1110, 6622, 257]]) #A 第一行对应第一段文本，第二行对应第二段文本。 ``` @@ -179,15 +179,15 @@ print(logits) ```python Output shape: torch.Size([2, 4, 50257]) tensor([[[-1.2034, 0.3201, -0.7130, ..., -1.5548, -0.2390, -0.4667], - [-0.1192, 0.4539, -0.4432, ..., 0.2392, 1.3469, 1.2430], - [ 0.5307, 1.6720, -0.4695, ..., 1.1966, 0.0111, 0.5835], - [ 0.0139, 1.6755, -0.3388, ..., 1.1586, -0.0435, -1.0400]], + [-0.1192, 0.4539, -0.4432, ..., 0.2392, 1.3469, 1.2430], + [ 0.5307, 1.6720, -0.4695, ..., 1.1966, 0.0111, 0.5835], + [ 0.0139, 1.6755, -0.3388, ..., 1.1586, -0.0435, -1.0400]], - [[-1.0908, 0.1798, -0.9484, ..., -1.6047, 0.2439, -0.4530], - [-0.7860, 0.5581, -0.0610, ..., 0.4835, -0.0077, 1.6621], - [ 0.3567, 1.2698, -0.6398, ..., -0.0162, -0.1296, 0.3717], - [-0.2407, -0.7349, -0.5102, ..., 2.0057, -0.3694, 0.1814]]], - grad_fn=) + [[-1.0908, 0.1798, -0.9484, ..., -1.6047, 0.2439, -0.4530], + [-0.7860, 0.5581, -0.0610, ..., 0.4835, -0.0077, 1.6621], + [ 0.3567, 1.2698, -0.6398, ..., -0.0162, -0.1296, 0.3717], + [-0.2407, -0.7349, -0.5102, ..., 2.0057, -0.3694, 0.1814]]], + grad_fn=) ``` 输出的张量有两行，每行对应一段文本。每段文本包含 4 个 token，每个 token 是一个 50,257 维的向量，维度大小与分词器的词汇表相同。