yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-09-26 16:52:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #183 from superkostya/fix-mha-wrapper-class

Browse Source 
Fix an incorrect input dimension
This commit is contained in:
Sebastian Raschka 2024-05-26 17:09:19 -04:00 committed by GitHub
commit f359db8a10
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
ch03/01_main-chapter-code/multihead-attention.ipynb
View File

@ -38,7 +38,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"torch version: 2.2.1\n" "torch version: 2.2.2\n"
] ]
} }
], ],
@ -365,6 +365,14 @@
"\n", "\n",
"print(\"context_vecs.shape:\", context_vecs.shape)" "print(\"context_vecs.shape:\", context_vecs.shape)"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f1d965a5-9b98-4554-8646-7ecd497874cb",
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {

2
ch03/02_bonus_efficient-multihead-attention/mha-implementations.ipynb
View File

@ -341,7 +341,7 @@
" self.d_out = d_out\n", " self.d_out = d_out\n",
"\n", "\n",
" self.qkv = nn.Linear(d_in, 3 * d_out, bias=qkv_bias)\n", " self.qkv = nn.Linear(d_in, 3 * d_out, bias=qkv_bias)\n",
" self.proj = nn.Linear(d_in, d_out)\n", " self.proj = nn.Linear(d_out, d_out)\n",
" self.dropout = dropout\n", " self.dropout = dropout\n",
"\n", "\n",
" def forward(self, x):\n", " def forward(self, x):\n",