yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-13 08:34:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Note about MPS devices (#329)

Browse Source
This commit is contained in:
Sebastian Raschka 2024-08-19 20:58:45 -05:00 committed by GitHub
parent a82169290e
commit 11e2f56af5
3 changed files with 43 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
appendix-D/01_main-chapter-code/appendix-D.ipynb
View File

@ -81,6 +81,20 @@
"\n", "\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"\n", "\n",
"# Note:\n",
"# Uncommenting the following lines will allow the code to run on Apple Silicon chips, if applicable,\n",
"# which is approximately 2x faster than on an Apple CPU (as measured on an M3 MacBook Air).\n",
"# However, the resulting loss values may be slightly different.\n",
"\n",
"#if torch.cuda.is_available():\n",
"# device = torch.device(\"cuda\")\n",
"#elif torch.backends.mps.is_available():\n",
"# device = torch.device(\"mps\")\n",
"#else:\n",
"# device = torch.device(\"cpu\")\n",
"#\n",
"# print(f\"Using {device} device.\")\n",
"\n",
"torch.manual_seed(123)\n", "torch.manual_seed(123)\n",
"model = GPTModel(GPT_CONFIG_124M)\n", "model = GPTModel(GPT_CONFIG_124M)\n",
"model.eval(); # Disable dropout during inference" "model.eval(); # Disable dropout during inference"
@ -660,6 +674,11 @@
"source": [ "source": [
"import tiktoken\n", "import tiktoken\n",
"\n", "\n",
"# Note:\n",
"# Uncomment the following code to calculate the execution time\n",
"# import time\n",
"# start_time = time.time()\n",
"\n",
"torch.manual_seed(123)\n", "torch.manual_seed(123)\n",
"model = GPTModel(GPT_CONFIG_124M)\n", "model = GPTModel(GPT_CONFIG_124M)\n",
"model.to(device)\n", "model.to(device)\n",
@ -674,7 +693,13 @@
" eval_freq=5, eval_iter=1, start_context=\"Every effort moves you\",\n", " eval_freq=5, eval_iter=1, start_context=\"Every effort moves you\",\n",
" tokenizer=tokenizer, warmup_steps=warmup_steps, \n", " tokenizer=tokenizer, warmup_steps=warmup_steps, \n",
" initial_lr=1e-5, min_lr=1e-5\n", " initial_lr=1e-5, min_lr=1e-5\n",
")" ")\n",
"\n",
"# Note:\n",
"# Uncomment the following code to show the execution time\n",
"# end_time = time.time()\n",
"# execution_time_minutes = (end_time - start_time) / 60\n",
"# print(f\"Training completed in {execution_time_minutes:.2f} minutes.\")"
] ]
}, },
{ {

15
appendix-E/01_main-chapter-code/appendix-E.ipynb
View File

@ -511,6 +511,21 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"\n",
"# Note:\n",
"# Uncommenting the following lines will allow the code to run on Apple Silicon chips, if applicable,\n",
"# which is approximately 1.2x faster than on an Apple CPU (as measured on an M3 MacBook Air).\n",
"# However, the resulting loss values may be slightly different.\n",
"\n",
"#if torch.cuda.is_available():\n",
"# device = torch.device(\"cuda\")\n",
"#elif torch.backends.mps.is_available():\n",
"# device = torch.device(\"mps\")\n",
"#else:\n",
"# device = torch.device(\"cpu\")\n",
"#\n",
"# print(f\"Using {device} device.\")\n",
"\n",
"model.to(device); # no assignment model = model.to(device) necessary for nn.Module classes" "model.to(device); # no assignment model = model.to(device) necessary for nn.Module classes"
] ]
}, },

2
ch05/01_main-chapter-code/ch05.ipynb
View File

@ -1154,6 +1154,8 @@
"# device = torch.device(\"mps\")\n", "# device = torch.device(\"mps\")\n",
"#else:\n", "#else:\n",
"# device = torch.device(\"cpu\")\n", "# device = torch.device(\"cpu\")\n",
"#\n",
"# print(f\"Using {device} device.\")\n",
"\n", "\n",
"\n", "\n",
"model.to(device) # no assignment model = model.to(device) necessary for nn.Module classes\n", "model.to(device) # no assignment model = model.to(device) necessary for nn.Module classes\n",