yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-10-23 13:59:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

update pr

Browse Source
This commit is contained in:
rasbt 2024-05-26 15:38:35 -05:00
parent 2088d75966
commit ec6e09136a
2 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
ch03/01_main-chapter-code/multihead-attention.ipynb
View File

@ -38,7 +38,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"torch version: 2.2.1\n"
"torch version: 2.2.2\n"
]
}
],
@ -228,7 +228,7 @@
" [CausalSelfAttention(d_in, d_out, context_length, dropout, qkv_bias) \n",
" for _ in range(num_heads)]\n",
" )\n",
" self.out_proj = nn.Linear(d_in*num_heads, d_out*num_heads)\n",
" self.out_proj = nn.Linear(d_out*num_heads, d_out*num_heads)\n",
"\n",
" def forward(self, x):\n",
" context_vec = torch.cat([head(x) for head in self.heads], dim=-1)\n",
@ -365,6 +365,14 @@
"\n",
"print(\"context_vecs.shape:\", context_vecs.shape)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f1d965a5-9b98-4554-8646-7ecd497874cb",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -383,7 +391,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
"version": "3.11.4"
}
},
"nbformat": 4,

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

@ -341,7 +341,7 @@
" self.d_out = d_out\n",
"\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",
"\n",
" def forward(self, x):\n",