mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2026-04-10 12:33:42 +00:00
committed by
GitHub
parent
6cbe6520a2
commit
08040f024c
@@ -28,6 +28,35 @@
|
||||
"# Chapter 5 Exercise solutions"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "37aa4692-2357-4d88-b072-6d2d988d7f4f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"numpy version: 1.26.4\n",
|
||||
"tiktoken version: 0.7.0\n",
|
||||
"torch version: 2.4.0\n",
|
||||
"tensorflow version: 2.16.1\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from importlib.metadata import version\n",
|
||||
"\n",
|
||||
"pkgs = [\"numpy\", \n",
|
||||
" \"tiktoken\", \n",
|
||||
" \"torch\",\n",
|
||||
" \"tensorflow\" # For OpenAI's pretrained weights\n",
|
||||
" ]\n",
|
||||
"for p in pkgs:\n",
|
||||
" print(f\"{p} version: {version(p)}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5fea8be3-30a1-4623-a6d7-b095c6c1092e",
|
||||
@@ -58,7 +87,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 2,
|
||||
"id": "42dda298-3014-4c36-8d63-97c210bcf4e8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -109,7 +138,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 3,
|
||||
"id": "b5605236-e300-4844-aea7-509d868efbdd",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -172,7 +201,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"id": "1d4163c0-22ad-4f5b-8e20-b7420e9dbfc6",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -182,7 +211,7 @@
|
||||
"tensor(0.0430)"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -250,7 +279,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 5,
|
||||
"id": "a61a4034-797a-4635-bf42-ddfff1b07125",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -275,13 +304,13 @@
|
||||
"\n",
|
||||
"tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
|
||||
"model = GPTModel(GPT_CONFIG_124M)\n",
|
||||
"model.load_state_dict(torch.load(\"model.pth\"))\n",
|
||||
"model.load_state_dict(torch.load(\"model.pth\", weights_only=True))\n",
|
||||
"model.eval();"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 6,
|
||||
"id": "ee95a272-b852-43b4-9827-ea7e1dbd5724",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -292,7 +321,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 7,
|
||||
"id": "4ab43658-3240-484a-9072-a40a0ed85be6",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -322,7 +351,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 8,
|
||||
"id": "ebb22d06-393a-42d3-ab64-66646d33b39b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -352,7 +381,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 9,
|
||||
"id": "75469f24-47cc-458d-a200-fe64c648131d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -400,7 +429,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 10,
|
||||
"id": "94eae6ba-d9fd-417a-8e31-fc39e9299870",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -424,7 +453,7 @@
|
||||
"\n",
|
||||
"tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
|
||||
"\n",
|
||||
"checkpoint = torch.load(\"model_and_optimizer.pth\")\n",
|
||||
"checkpoint = torch.load(\"model_and_optimizer.pth\", weights_only=True)\n",
|
||||
"model = GPTModel(GPT_CONFIG_124M)\n",
|
||||
"model.load_state_dict(checkpoint[\"model_state_dict\"])\n",
|
||||
"model.to(device)\n",
|
||||
@@ -444,7 +473,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 11,
|
||||
"id": "b5a78470-0652-4abd-875a-664e23c07c36",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -507,7 +536,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 12,
|
||||
"id": "ab4693dc-1359-47a7-8110-1e90f514a49e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -576,7 +605,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 13,
|
||||
"id": "68d162d6-bbb9-4d6d-82ee-1c410694f872",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -604,7 +633,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 14,
|
||||
"id": "d8373461-7dad-47da-a489-3e23f0799b23",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -630,7 +659,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": 15,
|
||||
"id": "cdd44873-d6c2-4471-a20f-f639b09fdcd3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -655,7 +684,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"execution_count": 16,
|
||||
"id": "c7d562e4-33f6-4611-9b75-6ad1cb441d3b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -670,7 +699,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": 17,
|
||||
"id": "46eda9ea-ccb0-46ee-931b-3c07502b2544",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -725,7 +754,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 18,
|
||||
"id": "4e3574a2-687d-47a2-a2f6-457fe9d595f1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -733,8 +762,8 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Training loss: 3.7547483444213867\n",
|
||||
"Validation loss: 3.5596189498901367\n"
|
||||
"Training loss: 3.7547486888037787\n",
|
||||
"Validation loss: 3.5596182346343994\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -759,23 +788,29 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 19,
|
||||
"id": "1a79a4b6-fe8f-40c2-a018-e731dcf391b3",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"checkpoint: 100%|███████████████████████████| 77.0/77.0 [00:00<00:00, 43.5kiB/s]\n",
|
||||
"encoder.json: 100%|███████████████████████| 1.04M/1.04M [00:00<00:00, 2.75MiB/s]\n",
|
||||
"hparams.json: 100%|█████████████████████████| 91.0/91.0 [00:00<00:00, 60.2kiB/s]\n",
|
||||
"model.ckpt.data-00000-of-00001: 100%|█████| 6.23G/6.23G [06:02<00:00, 17.2MiB/s]\n",
|
||||
"model.ckpt.index: 100%|████████████████████| 20.7k/20.7k [00:00<00:00, 171kiB/s]\n",
|
||||
"model.ckpt.meta: 100%|████████████████████| 1.84M/1.84M [00:00<00:00, 4.27MiB/s]\n",
|
||||
"vocab.bpe: 100%|████████████████████████████| 456k/456k [00:00<00:00, 1.73MiB/s]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"File already exists and is up-to-date: gpt2/1558M/checkpoint\n",
|
||||
"File already exists and is up-to-date: gpt2/1558M/encoder.json\n",
|
||||
"File already exists and is up-to-date: gpt2/1558M/hparams.json\n",
|
||||
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.data-00000-of-00001\n",
|
||||
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.index\n",
|
||||
"File already exists and is up-to-date: gpt2/1558M/model.ckpt.meta\n",
|
||||
"File already exists and is up-to-date: gpt2/1558M/vocab.bpe\n",
|
||||
"Training loss: 3.3046313656700983\n",
|
||||
"Validation loss: 3.1195149421691895\n"
|
||||
"Training loss: 3.3046312861972384\n",
|
||||
"Validation loss: 3.1195147037506104\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -832,7 +867,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 20,
|
||||
"id": "31e0972b-e85e-4904-a0f5-24c3eacd5fa2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -858,7 +893,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"execution_count": 21,
|
||||
"id": "b641ee88-f9d4-43ec-a787-e34199eed356",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -902,7 +937,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"execution_count": 22,
|
||||
"id": "c98f56f4-98fc-43b4-9ee5-726e9d17c73f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -912,7 +947,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"execution_count": 23,
|
||||
"id": "b1f7853c-6e81-4f1f-a1d0-61e2c7d33a20",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -957,7 +992,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.11"
|
||||
"version": "3.11.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user