add wording from three to four

This commit is contained in:
rasbt 2024-03-04 06:42:58 -06:00
parent 29672da3b0
commit 3198363c4f

View File

@ -26,7 +26,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"torch version: 2.2.1\n",
"torch version: 2.1.0\n",
"tiktoken version: 0.5.1\n"
]
}
@ -559,7 +559,7 @@
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[16], line 5\u001b[0m\n\u001b[1;32m 1\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m SimpleTokenizerV1(vocab)\n\u001b[1;32m 3\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHello, do you like tea. Is this-- a test?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 5\u001b[0m \u001b[43mtokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n",
"Cell \u001b[0;32mIn[12], line 9\u001b[0m, in \u001b[0;36mSimpleTokenizerV1.encode\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 7\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m([,.?_!\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m()\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m]|--|\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms)\u001b[39m\u001b[38;5;124m'\u001b[39m, text)\n\u001b[1;32m 8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()]\n\u001b[0;32m----> 9\u001b[0m ids \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43ms\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpreprocessed\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
"Cell \u001b[0;32mIn[12], line 9\u001b[0m, in \u001b[0;36mSimpleTokenizerV1.encode\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 7\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m([,.?_!\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m()\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m]|--|\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms)\u001b[39m\u001b[38;5;124m'\u001b[39m, text)\n\u001b[1;32m 8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()]\n\u001b[0;32m----> 9\u001b[0m ids \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstr_to_int[s] \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m preprocessed]\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
"Cell \u001b[0;32mIn[12], line 9\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 7\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m([,.?_!\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m()\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m]|--|\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms)\u001b[39m\u001b[38;5;124m'\u001b[39m, text)\n\u001b[1;32m 8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()]\n\u001b[0;32m----> 9\u001b[0m ids \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m preprocessed]\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
"\u001b[0;31mKeyError\u001b[0m: 'Hello'"
]
@ -585,7 +585,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 17,
"id": "ce9df29c-6c5b-43f1-8c1a-c7f7b79db78f",
"metadata": {},
"outputs": [],
@ -601,17 +601,17 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 18,
"id": "57c3143b-e860-4d3b-a22a-de22b547a6a9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1159"
"1161"
]
},
"execution_count": 17,
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@ -622,7 +622,7 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": 19,
"id": "50e51bb1-ae05-4aa8-a9ff-455b65ed1959",
"metadata": {},
"outputs": [
@ -630,11 +630,11 @@
"name": "stdout",
"output_type": "stream",
"text": [
"('yet', 1154)\n",
"('you', 1155)\n",
"('younger', 1156)\n",
"('your', 1157)\n",
"('yourself', 1158)\n"
"('yourself', 1158)\n",
"('<|endoftext|>', 1159)\n",
"('<|unk|>', 1160)\n"
]
}
],
@ -653,7 +653,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": 20,
"id": "948861c5-3f30-4712-a234-725f20d26f68",
"metadata": {},
"outputs": [],
@ -689,7 +689,7 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": 21,
"id": "effcef79-e0a5-4f4a-a43a-31dd94b9250a",
"metadata": {},
"outputs": [
@ -714,22 +714,34 @@
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": 22,
"id": "ddfe7346-398d-4bf8-99f1-5b071244ce95",
"metadata": {},
"outputs": [
{
"ename": "KeyError",
"evalue": "'<|unk|>'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[21], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n",
"Cell \u001b[0;32mIn[19], line 12\u001b[0m, in \u001b[0;36mSimpleTokenizerV2.encode\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()]\n\u001b[1;32m 9\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item \u001b[38;5;28;01mif\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstr_to_int \n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m<|unk|>\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed]\n\u001b[0;32m---> 12\u001b[0m ids \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43ms\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpreprocessed\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
"Cell \u001b[0;32mIn[19], line 12\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()]\n\u001b[1;32m 9\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item \u001b[38;5;28;01mif\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstr_to_int \n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m<|unk|>\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed]\n\u001b[0;32m---> 12\u001b[0m ids \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m preprocessed]\n\u001b[1;32m 13\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
"\u001b[0;31mKeyError\u001b[0m: '<|unk|>'"
"data": {
"text/plain": [
"[1160,\n",
" 5,\n",
" 362,\n",
" 1155,\n",
" 642,\n",
" 1000,\n",
" 10,\n",
" 1159,\n",
" 57,\n",
" 1013,\n",
" 981,\n",
" 1009,\n",
" 738,\n",
" 1013,\n",
" 1160,\n",
" 7]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
@ -738,10 +750,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 23,
"id": "0c350ff6-2734-4e84-9ec7-d578baa4ae1b",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"'<|unk|>, do you like tea? <|endoftext|> In the sunlit terraces of the <|unk|>.'"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.decode(tokenizer.encode(text))"
]
@ -769,7 +792,7 @@
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": 24,
"id": "ede1d41f-934b-4bf4-8184-54394a257a94",
"metadata": {},
"outputs": [],
@ -779,7 +802,7 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": 25,
"id": "48967a77-7d17-42bf-9e92-fc619d63a59e",
"metadata": {},
"outputs": [
@ -800,7 +823,7 @@
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": 26,
"id": "6ad3312f-a5f7-4efc-9d7d-8ea09d7b5128",
"metadata": {},
"outputs": [],
@ -810,7 +833,7 @@
},
{
"cell_type": "code",
"execution_count": 25,
"execution_count": 27,
"id": "5ff2cd85-7cfb-4325-b390-219938589428",
"metadata": {},
"outputs": [
@ -832,7 +855,7 @@
},
{
"cell_type": "code",
"execution_count": 26,
"execution_count": 28,
"id": "d26a48bb-f82e-41a8-a955-a1c9cf9d50ab",
"metadata": {},
"outputs": [
@ -860,7 +883,7 @@
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": 29,
"id": "848d5ade-fd1f-46c3-9e31-1426e315c71b",
"metadata": {},
"outputs": [
@ -891,7 +914,7 @@
},
{
"cell_type": "code",
"execution_count": 28,
"execution_count": 30,
"id": "e84424a7-646d-45b6-99e3-80d15fb761f2",
"metadata": {},
"outputs": [],
@ -901,7 +924,7 @@
},
{
"cell_type": "code",
"execution_count": 29,
"execution_count": 31,
"id": "dfbff852-a92f-48c8-a46d-143a0f109f40",
"metadata": {},
"outputs": [
@ -934,7 +957,7 @@
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 32,
"id": "d97b031e-ed55-409d-95f2-aeb38c6fe366",
"metadata": {},
"outputs": [
@ -959,7 +982,7 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 33,
"id": "f57bd746-dcbf-4433-8e24-ee213a8c34a1",
"metadata": {},
"outputs": [
@ -1001,7 +1024,7 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 34,
"id": "e1770134-e7f3-4725-a679-e04c3be48cac",
"metadata": {},
"outputs": [
@ -1009,7 +1032,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"PyTorch version: 2.2.1\n"
"PyTorch version: 2.1.0\n"
]
}
],
@ -1028,7 +1051,7 @@
},
{
"cell_type": "code",
"execution_count": 33,
"execution_count": 35,
"id": "74b41073-4c9f-46e2-a1bd-d38e4122b375",
"metadata": {},
"outputs": [],
@ -1061,7 +1084,7 @@
},
{
"cell_type": "code",
"execution_count": 34,
"execution_count": 36,
"id": "5eb30ebe-97b3-43c5-9ff1-a97d621b3c4e",
"metadata": {},
"outputs": [],
@ -1091,7 +1114,7 @@
},
{
"cell_type": "code",
"execution_count": 35,
"execution_count": 37,
"id": "df31d96c-6bfd-4564-a956-6192242d7579",
"metadata": {},
"outputs": [],
@ -1102,7 +1125,7 @@
},
{
"cell_type": "code",
"execution_count": 36,
"execution_count": 38,
"id": "9226d00c-ad9a-4949-a6e4-9afccfc7214f",
"metadata": {},
"outputs": [
@ -1124,7 +1147,7 @@
},
{
"cell_type": "code",
"execution_count": 37,
"execution_count": 39,
"id": "10deb4bc-4de1-4d20-921e-4b1c7a0e1a6d",
"metadata": {},
"outputs": [
@ -1152,7 +1175,7 @@
},
{
"cell_type": "code",
"execution_count": 38,
"execution_count": 40,
"id": "1916e7a6-f03d-4f09-91a6-d0bdbac5a58c",
"metadata": {},
"outputs": [
@ -1214,12 +1237,12 @@
"id": "44e014ca-1fc5-4b90-b6fa-c2097bb92c0b",
"metadata": {},
"source": [
"- Suppose we have the following three input examples with input ids 5, 1, 3, and 2 (after tokenization):"
"- Suppose we have the following four input examples with input ids 5, 1, 3, and 2 (after tokenization):"
]
},
{
"cell_type": "code",
"execution_count": 39,
"execution_count": 41,
"id": "15a6304c-9474-4470-b85d-3991a49fa653",
"metadata": {},
"outputs": [],
@ -1237,7 +1260,7 @@
},
{
"cell_type": "code",
"execution_count": 40,
"execution_count": 42,
"id": "93cb2cee-9aa6-4bb8-8977-c65661d16eda",
"metadata": {},
"outputs": [],
@ -1259,7 +1282,7 @@
},
{
"cell_type": "code",
"execution_count": 41,
"execution_count": 43,
"id": "a686eb61-e737-4351-8f1c-222913d47468",
"metadata": {},
"outputs": [
@ -1300,7 +1323,7 @@
},
{
"cell_type": "code",
"execution_count": 42,
"execution_count": 44,
"id": "e43600ba-f287-4746-8ddf-d0f71a9023ca",
"metadata": {},
"outputs": [
@ -1327,7 +1350,7 @@
},
{
"cell_type": "code",
"execution_count": 43,
"execution_count": 45,
"id": "50280ead-0363-44c8-8c35-bb885d92c8b7",
"metadata": {},
"outputs": [
@ -1365,7 +1388,7 @@
},
{
"cell_type": "code",
"execution_count": 44,
"execution_count": 46,
"id": "0b9e344d-03a6-4f2c-b723-67b6a20c5041",
"metadata": {},
"outputs": [],
@ -1387,7 +1410,7 @@
},
{
"cell_type": "code",
"execution_count": 45,
"execution_count": 47,
"id": "ad56a263-3d2e-4d91-98bf-d0b68d3c7fc3",
"metadata": {},
"outputs": [],
@ -1400,7 +1423,7 @@
},
{
"cell_type": "code",
"execution_count": 46,
"execution_count": 48,
"id": "84416b60-3707-4370-bcbc-da0b62f2b64d",
"metadata": {},
"outputs": [
@ -1430,7 +1453,7 @@
},
{
"cell_type": "code",
"execution_count": 47,
"execution_count": 49,
"id": "7766ec38-30d0-4128-8c31-f49f063c43d1",
"metadata": {},
"outputs": [
@ -1457,7 +1480,7 @@
},
{
"cell_type": "code",
"execution_count": 53,
"execution_count": 50,
"id": "cc048e20-7ac8-417e-81f5-8fe6f9a4fe07",
"metadata": {},
"outputs": [],
@ -1468,7 +1491,7 @@
},
{
"cell_type": "code",
"execution_count": 54,
"execution_count": 51,
"id": "c369a1e7-d566-4b53-b398-d6adafb44105",
"metadata": {},
"outputs": [
@ -1495,7 +1518,7 @@
},
{
"cell_type": "code",
"execution_count": 55,
"execution_count": 52,
"id": "b22fab89-526e-43c8-9035-5b7018e34288",
"metadata": {},
"outputs": [
@ -1547,7 +1570,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.12"
}
},
"nbformat": 4,