Merge pull request #27 from 0-yy-0/gly

add:翻译 5.1
This commit is contained in:
Ethan-Chen-plus
2024-05-12 17:48:57 +08:00
committed by GitHub
2 changed files with 1952 additions and 2 deletions
@@ -75,7 +75,7 @@
"import tiktoken\n",
"\n",
"tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
"with open(\"/Users/zhihu123/Project/other/llms-from-scratch-cn/ch02/01_main-chapter-code/the-verdict.txt\", \"r\", encoding=\"utf-8\") as f:\n",
"with open(\"the-verdict.txt\", \"r\", encoding=\"utf-8\") as f:\n",
" raw_text = f.read()\n",
"enc_text = tokenizer.encode(raw_text)\n",
"print(len(enc_text))"
@@ -441,7 +441,7 @@
}
],
"source": [
"with open(\"/Users/zhihu123/Project/other/llms-from-scratch-cn/ch02/01_main-chapter-code/the-verdict.txt\", \"r\", encoding=\"utf-8\") as f:\n",
"with open(\"the-verdict.txt\", \"r\", encoding=\"utf-8\") as f:\n",
" raw_text = f.read()\n",
" dataloader = create_dataloader_v1(\n",
" raw_text, batch_size=1, max_length=4, stride=1, shuffle=False)\n",
File diff suppressed because it is too large Load Diff