mirror of
				https://github.com/rasbt/LLMs-from-scratch.git
				synced 2025-11-04 03:40:21 +00:00 
			
		
		
		
	format the other GPT architecture sizes
This commit is contained in:
		
							parent
							
								
									40477c55b3
								
							
						
					
					
						commit
						496b52f842
					
				@ -884,7 +884,7 @@
 | 
			
		||||
   "source": [
 | 
			
		||||
    "torch.manual_seed(123)\n",
 | 
			
		||||
    "\n",
 | 
			
		||||
    "x = torch.rand(2, 6, 768)\n",
 | 
			
		||||
    "x = torch.rand(2, 6, 768)  # Shape: [batch_size, num_tokens, emb_dim]\n",
 | 
			
		||||
    "block = TransformerBlock(GPT_CONFIG_124M)\n",
 | 
			
		||||
    "output = block(x)\n",
 | 
			
		||||
    "\n",
 | 
			
		||||
@ -1140,27 +1140,27 @@
 | 
			
		||||
   "id": "309a3be4-c20a-4657-b4e0-77c97510b47c",
 | 
			
		||||
   "metadata": {},
 | 
			
		||||
   "source": [
 | 
			
		||||
    "- Exercise: you can try the other configurations as well:\n",
 | 
			
		||||
    "- Exercise: you can try the following other configurations, which are referenced in the [GPT-2 paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf), as well.\n",
 | 
			
		||||
    "\n",
 | 
			
		||||
    "- GPT2-small (the 124M configuration we implemented):\n",
 | 
			
		||||
    "    - \"emb_dim\" = 768\n",
 | 
			
		||||
    "    - \"n_layers\" = 12\n",
 | 
			
		||||
    "    - \"n_heads\" = 12\n",
 | 
			
		||||
    "    - **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"
 | 
			
		||||
    "    - **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"
 | 
			
		||||
   ]
 | 
			
		||||
  },
 | 
			
		||||
  {
 | 
			
		||||
 | 
			
		||||
		Loading…
	
	
			
			x
			
			
		
	
		Reference in New Issue
	
	Block a user