books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Test code in pytorch 2.4 (#285)

Browse Source 
* test code in pytorch 2.4

* update
This commit is contained in:
Sebastian Raschka
2024-07-24 21:53:41 -05:00
committed by GitHub
parent 6cbe6520a2
commit 08040f024c
17 changed files with 509 additions and 377 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
appendix-A/01_main-chapter-code/code-part1.ipynb
View File

@@ -46,7 +46,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"2.2.1\n"
"2.4.0\n"
]
}
],
@@ -658,13 +658,13 @@
"output_type": "stream",
"text": [
"Parameter containing:\n",
"tensor([[ 0.0956, 0.1280, -0.0696, ..., 0.0961, 0.0631, 0.1349],\n",
" [ 0.0983, 0.0580, -0.0574, ..., 0.0981, 0.0370, 0.0516],\n",
" [-0.0429, -0.1411, -0.1399, ..., 0.0767, 0.0019, 0.1400],\n",
"tensor([[ 0.1182, 0.0606, -0.1292, ..., -0.1126, 0.0735, -0.0597],\n",
" [-0.0249, 0.0154, -0.0476, ..., -0.1001, -0.1288, 0.1295],\n",
" [ 0.0641, 0.0018, -0.0367, ..., -0.0990, -0.0424, -0.0043],\n",
" ...,\n",
" [-0.0777, -0.0726, 0.1273, ..., -0.0613, 0.0491, -0.1381],\n",
" [-0.0830, -0.0969, -0.0473, ..., 0.0762, 0.1318, -0.1174],\n",
" [ 0.0468, -0.0213, 0.0387, ..., 0.0639, 0.0927, -0.0668]],\n",
" [ 0.0618, 0.0867, 0.1361, ..., -0.0254, 0.0399, 0.1006],\n",
" [ 0.0842, -0.0512, -0.0960, ..., -0.1091, 0.1242, -0.0428],\n",
" [ 0.0518, -0.1390, -0.0923, ..., -0.0954, -0.0668, -0.0037]],\n",
" requires_grad=True)\n"
]
}
@@ -1264,7 +1264,7 @@
],
"source": [
"model = NeuralNetwork(2, 2) # needs to match the original model exactly\n",
"model.load_state_dict(torch.load(\"model.pth\"))"
"model.load_state_dict(torch.load(\"model.pth\", weights_only=True))"
]
},
{
@@ -1340,7 +1340,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
"version": "3.11.4"
}
},
"nbformat": 4,

79
appendix-A/01_main-chapter-code/code-part2.ipynb
View File

@@ -2,7 +2,9 @@
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"id": "AAAnDw04iAm4"
},
"source": [
"<table style=\"width:100%\">\n",
"<tr>\n",
@@ -54,14 +56,14 @@
"base_uri": "https://localhost:8080/"
},
"id": "RM7kGhwMF_nO",
"outputId": "ac60b048-b81f-4bb0-90fa-1ca474f04e9a"
"outputId": "b1872617-aacd-46fa-e5f3-f130fd81b246"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.0.1+cu118\n"
"2.4.0+cu121\n"
]
}
],
@@ -79,7 +81,7 @@
"base_uri": "https://localhost:8080/"
},
"id": "OXLCKXhiUkZt",
"outputId": "39fe5366-287e-47eb-cc34-3508d616c4f9"
"outputId": "e9ca3c58-d92c-4c8b-a9c9-cd7fcc1fedb4"
},
"outputs": [
{
@@ -102,18 +104,15 @@
"base_uri": "https://localhost:8080/"
},
"id": "MTTlfh53Va-T",
"outputId": "f31d8bbe-577f-4db4-9939-02e66b9f96d1"
"outputId": "bae76cb5-d1d3-441f-a7c5-93a161e2e86a"
},
"outputs": [
{
"data": {
"text/plain": [
"tensor([5., 7., 9.])"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
"name": "stdout",
"output_type": "stream",
"text": [
"tensor([5., 7., 9.])\n"
]
}
],
"source": [
@@ -125,13 +124,13 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Z4LwTNw7Vmmb",
"outputId": "1c025c6a-e3ed-4c7c-f5fd-86c14607036e"
"outputId": "9ad97923-bc8e-4c49-88bf-48dc1de56804"
},
"outputs": [
{
@@ -151,24 +150,24 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 184
"height": 158
},
"id": "tKT6URN1Vuft",
"outputId": "e6f01e7f-d9cf-44cb-cc6d-46fc7907d5c0"
"outputId": "8396eb18-47c8-47a1-c1b6-8bcb9480fb52"
},
"outputs": [
{
"ename": "RuntimeError",
"evalue": "ignored",
"evalue": "Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-7-4ff3c4d20fc3>\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mtensor_1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtensor_1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"cpu\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensor_1\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mtensor_2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m/tmp/ipykernel_2321/2079609735.py\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mtensor_1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtensor_1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"cpu\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensor_1\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mtensor_2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mRuntimeError\u001b[0m: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!"
]
}
@@ -189,7 +188,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 6,
"metadata": {
"id": "GyY59cjieitv"
},
@@ -215,7 +214,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 7,
"metadata": {
"id": "v41gKqEJempa"
},
@@ -243,7 +242,7 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": 8,
"metadata": {
"id": "UPGVRuylep8Y"
},
@@ -271,7 +270,7 @@
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": 9,
"metadata": {
"id": "drhg6IXofAXh"
},
@@ -302,13 +301,13 @@
},
{
"cell_type": "code",
"execution_count": 25,
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "7jaS5sqPWCY0",
"outputId": "84c74615-38f2-48b8-eeda-b5912fed1d3a"
"outputId": "8a5cd93d-671c-4abf-d5cd-97845f300ffd"
},
"outputs": [
{
@@ -362,7 +361,7 @@
},
{
"cell_type": "code",
"execution_count": 26,
"execution_count": 11,
"metadata": {
"id": "4qrlmnPPe7FO"
},
@@ -391,13 +390,13 @@
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "1_-BfkfEf4HX",
"outputId": "473bf21d-5880-4de3-fc8a-051d75315b94"
"outputId": "9453154f-0a5b-4a44-a3c9-f010e08d5a2c"
},
"outputs": [
{
@@ -406,7 +405,7 @@
"1.0"
]
},
"execution_count": 27,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -417,13 +416,13 @@
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "iYtXKBGEgKss",
"outputId": "508edd84-3fb7-4d04-cb23-9df0c3d24170"
"outputId": "d6cc870a-34de-490e-e5d3-23e6956744bd"
},
"outputs": [
{
@@ -432,7 +431,7 @@
"1.0"
]
},
"execution_count": 21,
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
@@ -443,21 +442,27 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"id": "nc2LGFVbiAnB"
},
"source": [
"### A.9.3 Training with multiple GPUs"
]
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"id": "cOUza9iQiAnC"
},
"source": [
"See [DDP-script.py](DDP-script.py)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"id": "YOYk5Fh7iAnC"
},
"source": [
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/12.webp\" width=\"600px\">\n",
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/13.webp\" width=\"600px\">"
@@ -485,7 +490,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.14"
}
},
"nbformat": 4,