mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2026-04-10 12:33:42 +00:00
118 lines
3.3 KiB
Plaintext
118 lines
3.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "98efe79e-daa3-40d0-ab4d-f667d4d6ba9d",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/Users/Author/miniforge3/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
|
|
" from .autonotebook import tqdm as notebook_tqdm\n",
|
|
"Downloading (…)olve/main/vocab.json: 100%|█| 1.04M/1.04M [00:00<00:00, 1.66MB/s]\n",
|
|
"Downloading (…)olve/main/merges.txt: 100%|███| 456k/456k [00:00<00:00, 2.44MB/s]\n",
|
|
"Downloading (…)/main/tokenizer.json: 100%|█| 1.36M/1.36M [00:00<00:00, 1.97MB/s]\n",
|
|
"Downloading (…)lve/main/config.json: 100%|██████| 718/718 [00:00<00:00, 621kB/s]\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Decoded Inputs:\n",
|
|
"I HAD always\n",
|
|
" Jack Gisburn\n",
|
|
" a cheap genius--\n",
|
|
" a good fellow enough\n",
|
|
"so it was no\n",
|
|
" surprise to me to\n",
|
|
" that, in the\n",
|
|
" of his glory,\n",
|
|
"\n",
|
|
"Decoded Targets:\n",
|
|
" HAD always thought\n",
|
|
" Gisburn rather\n",
|
|
" cheap genius--though\n",
|
|
" good fellow enough--\n",
|
|
" it was no great\n",
|
|
" to me to hear\n",
|
|
", in the height\n",
|
|
" his glory, he\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import torch\n",
|
|
"from transformers import GPT2Tokenizer\n",
|
|
"\n",
|
|
"tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')\n",
|
|
"\n",
|
|
"inputs = torch.tensor([\n",
|
|
" [40, 367, 2885, 1464],\n",
|
|
" [3619, 402, 271, 10899],\n",
|
|
" [257, 7026, 15632, 438],\n",
|
|
" [257, 922, 5891, 1576],\n",
|
|
" [568, 340, 373, 645],\n",
|
|
" [5975, 284, 502, 284],\n",
|
|
" [326, 11, 287, 262],\n",
|
|
" [286, 465, 13476, 11]\n",
|
|
"])\n",
|
|
"\n",
|
|
"targets = torch.tensor([\n",
|
|
" [367, 2885, 1464, 1807],\n",
|
|
" [402, 271, 10899, 2138],\n",
|
|
" [7026, 15632, 438, 2016],\n",
|
|
" [922, 5891, 1576, 438],\n",
|
|
" [340, 373, 645, 1049],\n",
|
|
" [284, 502, 284, 3285],\n",
|
|
" [11, 287, 262, 6001],\n",
|
|
" [465, 13476, 11, 339]\n",
|
|
"])\n",
|
|
"\n",
|
|
"decoded_inputs = [tokenizer.decode(i) for i in inputs]\n",
|
|
"decoded_targets = [tokenizer.decode(t) for t in targets]\n",
|
|
"\n",
|
|
"print(\"Decoded Inputs:\")\n",
|
|
"for di in decoded_inputs:\n",
|
|
" print(di)\n",
|
|
"\n",
|
|
"print(\"\\nDecoded Targets:\")\n",
|
|
"for dt in decoded_targets:\n",
|
|
" print(dt)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "defc6b2f-9ac2-49e0-a4e1-03247cacffce",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.10.12"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|