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

rearrange exercise order

Browse Source
This commit is contained in:
rasbt
2024-02-11 14:46:05 -06:00
parent 79d90d8147
commit 1d6f2c9084
1 changed files with 228 additions and 229 deletions
Download Patch File Download Diff File Expand all files Collapse all files

457
ch04/01_main-chapter-code/exercise-solutions.ipynb
View File

@@ -10,15 +10,239 @@
},
{
"cell_type": "markdown",
"id": "33dfa199-9aee-41d4-a64b-7e3811b9a616",
"id": "5fea8be3-30a1-4623-a6d7-b095c6c1092e",
"metadata": {},
"source": [
"# Exercise 4.1: Using separate dropout parameters"
"# Exercise 4.1: Parameters in the feed forward versus attention module"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "2751b0e5-ffd3-4be2-8db3-e20dd4d61d69",
"metadata": {},
"outputs": [],
"source": [
"from gpt import TransformerBlock\n",
"\n",
"GPT_CONFIG_124M = {\n",
" \"vocab_size\": 50257,\n",
" \"ctx_len\": 1024,\n",
" \"emb_dim\": 768,\n",
" \"n_heads\": 12,\n",
" \"n_layers\": 12,\n",
" \"drop_rate\": 0.1,\n",
" \"qkv_bias\": False\n",
"}\n",
"\n",
"block = TransformerBlock(GPT_CONFIG_124M)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1bcaffd1-0cf6-4f8f-bd53-ab88a37f443e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total number of parameters in feed forward module: 4,722,432\n"
]
}
],
"source": [
"total_params = sum(p.numel() for p in block.ff.parameters())\n",
"print(f\"Total number of parameters in feed forward module: {total_params:,}\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "c1dd06c1-ab6c-4df7-ba73-f9cd54b31138",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total number of parameters in attention module: 2,360,064\n"
]
}
],
"source": [
"total_params = sum(p.numel() for p in block.att.parameters())\n",
"print(f\"Total number of parameters in attention module: {total_params:,}\")"
]
},
{
"cell_type": "markdown",
"id": "15463dec-520a-47b4-b3ad-e180394fd076",
"metadata": {},
"source": [
"- The results above are for a single transformer block\n",
"- Optionally multiply by 12 to capture all transformer blocks in the 124M GPT model"
]
},
{
"cell_type": "markdown",
"id": "0f7b7c7f-0fa1-4d30-ab44-e499edd55b6d",
"metadata": {},
"source": [
"# Exercise 4.2: Initialize larger GPT models"
]
},
{
"cell_type": "markdown",
"id": "310b2e05-3ec8-47fc-afd9-83bf03d4aad8",
"metadata": {},
"source": [
"- **GPT2-small** (the 124M configuration we already implemented):\n",
" - \"emb_dim\" = 768\n",
" - \"n_layers\" = 12\n",
" - \"n_heads\" = 12\n",
"\n",
"- **GPT2-medium:**\n",
" - \"emb_dim\" = 1024\n",
" - \"n_layers\" = 24\n",
" - \"n_heads\" = 16\n",
"\n",
"- **GPT2-large:**\n",
" - \"emb_dim\" = 1280\n",
" - \"n_layers\" = 36\n",
" - \"n_heads\" = 20\n",
"\n",
"- **GPT2-XL:**\n",
" - \"emb_dim\" = 1600\n",
" - \"n_layers\" = 48\n",
" - \"n_heads\" = 25"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "90185dea-81ca-4cdc-aef7-4aaf95cba946",
"metadata": {},
"outputs": [],
"source": [
"GPT_CONFIG_124M = {\n",
" \"vocab_size\": 50257,\n",
" \"ctx_len\": 1024,\n",
" \"emb_dim\": 768,\n",
" \"n_heads\": 12,\n",
" \"n_layers\": 12,\n",
" \"drop_rate\": 0.1,\n",
" \"qkv_bias\": False\n",
"}\n",
"\n",
"\n",
"def get_config(base_config, model_name=\"gpt2-small\"):\n",
" GPT_CONFIG = base_config.copy()\n",
"\n",
" if model_name == \"gpt2-small\":\n",
" GPT_CONFIG[\"emb_dim\"] = 768\n",
" GPT_CONFIG[\"n_layers\"] = 12\n",
" GPT_CONFIG[\"n_heads\"] = 12\n",
"\n",
" elif model_name == \"gpt2-medium\":\n",
" GPT_CONFIG[\"emb_dim\"] = 1024\n",
" GPT_CONFIG[\"n_layers\"] = 24\n",
" GPT_CONFIG[\"n_heads\"] = 16\n",
"\n",
" elif model_name == \"gpt2-large\":\n",
" GPT_CONFIG[\"emb_dim\"] = 1280\n",
" GPT_CONFIG[\"n_layers\"] = 36\n",
" GPT_CONFIG[\"n_heads\"] = 20\n",
"\n",
" elif model_name == \"gpt2-xl\":\n",
" GPT_CONFIG[\"emb_dim\"] = 1600\n",
" GPT_CONFIG[\"n_layers\"] = 48\n",
" GPT_CONFIG[\"n_heads\"] = 25\n",
"\n",
" else:\n",
" raise ValueError(f\"Incorrect model name {model_name}\")\n",
"\n",
" return GPT_CONFIG\n",
"\n",
"\n",
"def calculate_size(model): # based on chapter code\n",
" \n",
" total_params = sum(p.numel() for p in model.parameters())\n",
" print(f\"Total number of parameters: {total_params:,}\")\n",
"\n",
" total_params_gpt2 = total_params - sum(p.numel() for p in model.out_head.parameters())\n",
" print(f\"Number of trainable parameters considering weight tying: {total_params_gpt2:,}\")\n",
" \n",
" # Calculate the total size in bytes (assuming float32, 4 bytes per parameter)\n",
" total_size_bytes = total_params * 4\n",
" \n",
" # Convert to megabytes\n",
" total_size_mb = total_size_bytes / (1024 * 1024)\n",
" \n",
" print(f\"Total size of the model: {total_size_mb:.2f} MB\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2587e011-78a4-479c-a8fd-961cc40a5fd4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"gpt2-small:\n",
"Total number of parameters: 163,009,536\n",
"Number of trainable parameters considering weight tying: 124,412,160\n",
"Total size of the model: 621.83 MB\n",
"\n",
"\n",
"gpt2-medium:\n",
"Total number of parameters: 406,212,608\n",
"Number of trainable parameters considering weight tying: 354,749,440\n",
"Total size of the model: 1549.58 MB\n",
"\n",
"\n",
"gpt2-large:\n",
"Total number of parameters: 838,220,800\n",
"Number of trainable parameters considering weight tying: 773,891,840\n",
"Total size of the model: 3197.56 MB\n",
"\n",
"\n",
"gpt2-xl:\n",
"Total number of parameters: 1,637,792,000\n",
"Number of trainable parameters considering weight tying: 1,557,380,800\n",
"Total size of the model: 6247.68 MB\n"
]
}
],
"source": [
"from gpt import GPTModel\n",
"\n",
"\n",
"for model_abbrev in (\"small\", \"medium\", \"large\", \"xl\"):\n",
" model_name = f\"gpt2-{model_abbrev}\"\n",
" CONFIG = get_config(GPT_CONFIG_124M, model_name=model_name)\n",
" model = GPTModel(CONFIG)\n",
" print(f\"\\n\\n{model_name}:\")\n",
" calculate_size(model)"
]
},
{
"cell_type": "markdown",
"id": "f5f2306e-5dc8-498e-92ee-70ae7ec37ac1",
"metadata": {},
"source": [
"# Exercise 4.3: Using separate dropout parameters"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "5fee2cf5-61c3-4167-81b5-44ea155bbaf2",
"metadata": {},
"outputs": [],
@@ -39,7 +263,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 7,
"id": "5aa1b0c1-d78a-48fc-ad08-4802458b43f7",
"metadata": {},
"outputs": [],
@@ -120,241 +344,16 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 8,
"id": "1d013d32-c275-4f42-be21-9010f1537227",
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"import tiktoken\n",
"\n",
"torch.manual_seed(123)\n",
"model = GPTModel(GPT_CONFIG_124M)"
]
},
{
"cell_type": "markdown",
"id": "5fea8be3-30a1-4623-a6d7-b095c6c1092e",
"metadata": {},
"source": [
"# Exercise 4.2: Parameters in the feed forward versus attention module"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "2751b0e5-ffd3-4be2-8db3-e20dd4d61d69",
"metadata": {},
"outputs": [],
"source": [
"from gpt import TransformerBlock\n",
"\n",
"GPT_CONFIG_124M = {\n",
" \"vocab_size\": 50257,\n",
" \"ctx_len\": 1024,\n",
" \"emb_dim\": 768,\n",
" \"n_heads\": 12,\n",
" \"n_layers\": 12,\n",
" \"drop_rate\": 0.1,\n",
" \"qkv_bias\": False\n",
"}\n",
"\n",
"model = TransformerBlock(GPT_CONFIG_124M)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "1bcaffd1-0cf6-4f8f-bd53-ab88a37f443e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total number of parameters in feed forward module: 4,722,432\n"
]
}
],
"source": [
"total_params = sum(p.numel() for p in block.ff.parameters())\n",
"print(f\"Total number of parameters in feed forward module: {total_params:,}\")"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "c1dd06c1-ab6c-4df7-ba73-f9cd54b31138",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total number of parameters in feed forward module: 2,360,064\n"
]
}
],
"source": [
"total_params = sum(p.numel() for p in block.att.parameters())\n",
"print(f\"Total number of parameters in attention module: {total_params:,}\")"
]
},
{
"cell_type": "markdown",
"id": "15463dec-520a-47b4-b3ad-e180394fd076",
"metadata": {},
"source": [
"- The results above are for a single transformer block\n",
"- Optionally multiply by 12 to capture all transformer blocks in the 124M GPT model"
]
},
{
"cell_type": "markdown",
"id": "0f7b7c7f-0fa1-4d30-ab44-e499edd55b6d",
"metadata": {},
"source": [
"# Exercise 4.3: Initialize larger GPT models"
]
},
{
"cell_type": "markdown",
"id": "310b2e05-3ec8-47fc-afd9-83bf03d4aad8",
"metadata": {},
"source": [
"- **GPT2-small** (the 124M configuration we already implemented):\n",
" - \"emb_dim\" = 768\n",
" - \"n_layers\" = 12\n",
" - \"n_heads\" = 12\n",
"\n",
"- **GPT2-medium:**\n",
" - \"emb_dim\" = 1024\n",
" - \"n_layers\" = 24\n",
" - \"n_heads\" = 16\n",
"\n",
"- **GPT2-large:**\n",
" - \"emb_dim\" = 1280\n",
" - \"n_layers\" = 36\n",
" - \"n_heads\" = 20\n",
"\n",
"- **GPT2-XL:**\n",
" - \"emb_dim\" = 1600\n",
" - \"n_layers\" = 48\n",
" - \"n_heads\" = 25"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "90185dea-81ca-4cdc-aef7-4aaf95cba946",
"metadata": {},
"outputs": [],
"source": [
"GPT_CONFIG_124M = {\n",
" \"vocab_size\": 50257,\n",
" \"ctx_len\": 1024,\n",
" \"emb_dim\": 768,\n",
" \"n_heads\": 12,\n",
" \"n_layers\": 12,\n",
" \"drop_rate\": 0.1,\n",
" \"qkv_bias\": False\n",
"}\n",
"\n",
"\n",
"def get_config(base_config, model_name=\"gpt2-small\"):\n",
" GPT_CONFIG = base_config.copy()\n",
"\n",
" if model_name == \"gpt2-small\":\n",
" GPT_CONFIG[\"emb_dim\"] = 768\n",
" GPT_CONFIG[\"n_layers\"] = 12\n",
" GPT_CONFIG[\"n_heads\"] = 12\n",
"\n",
" elif model_name == \"gpt2-medium\":\n",
" GPT_CONFIG[\"emb_dim\"] = 1024\n",
" GPT_CONFIG[\"n_layers\"] = 24\n",
" GPT_CONFIG[\"n_heads\"] = 16\n",
"\n",
" elif model_name == \"gpt2-large\":\n",
" GPT_CONFIG[\"emb_dim\"] = 1280\n",
" GPT_CONFIG[\"n_layers\"] = 36\n",
" GPT_CONFIG[\"n_heads\"] = 20\n",
"\n",
" elif model_name == \"gpt2-xl\":\n",
" GPT_CONFIG[\"emb_dim\"] = 1600\n",
" GPT_CONFIG[\"n_layers\"] = 48\n",
" GPT_CONFIG[\"n_heads\"] = 25\n",
"\n",
" else:\n",
" raise ValueError(f\"Incorrect model name {model_name}\")\n",
"\n",
" return GPT_CONFIG\n",
"\n",
"\n",
"def calculate_size(model): # based on chapter code\n",
" \n",
" total_params = sum(p.numel() for p in model.parameters())\n",
" print(f\"Total number of parameters: {total_params:,}\")\n",
"\n",
" total_params_gpt2 = total_params - sum(p.numel() for p in model.out_head.parameters())\n",
" print(f\"Number of trainable parameters considering weight tying: {total_params_gpt2:,}\")\n",
" \n",
" # Calculate the total size in bytes (assuming float32, 4 bytes per parameter)\n",
" total_size_bytes = total_params * 4\n",
" \n",
" # Convert to megabytes\n",
" total_size_mb = total_size_bytes / (1024 * 1024)\n",
" \n",
" print(f\"Total size of the model: {total_size_mb:.2f} MB\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "2587e011-78a4-479c-a8fd-961cc40a5fd4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"gpt2-small:\n",
"Total number of parameters: 163,009,536\n",
"Number of trainable parameters considering weight tying: 124,412,160\n",
"Total size of the model: 621.83 MB\n",
"\n",
"\n",
"gpt2-medium:\n",
"Total number of parameters: 406,212,608\n",
"Number of trainable parameters considering weight tying: 354,749,440\n",
"Total size of the model: 1549.58 MB\n",
"\n",
"\n",
"gpt2-large:\n",
"Total number of parameters: 838,220,800\n",
"Number of trainable parameters considering weight tying: 773,891,840\n",
"Total size of the model: 3197.56 MB\n",
"\n",
"\n",
"gpt2-xl:\n",
"Total number of parameters: 1,637,792,000\n",
"Number of trainable parameters considering weight tying: 1,557,380,800\n",
"Total size of the model: 6247.68 MB\n"
]
}
],
"source": [
"from gpt import GPTModel\n",
"\n",
"\n",
"for model_abbrev in (\"small\", \"medium\", \"large\", \"xl\"):\n",
" model_name = f\"gpt2-{model_abbrev}\"\n",
" CONFIG = get_config(GPT_CONFIG_124M, model_name=model_name)\n",
" model = GPTModel(CONFIG)\n",
" print(f\"\\n\\n{model_name}:\")\n",
" calculate_size(model)"
]
}
],
"metadata": {