yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-02 19:00:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

rename q,k,v for consistency with chapter 3

Browse Source
This commit is contained in:
rasbt 2024-03-07 06:30:40 -06:00
parent 496079c61e
commit 99a5e28def
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
ch03/02_bonus_efficient-multihead-attention/mha-implementations.ipynb
View File

@ -259,11 +259,11 @@
" qkv = qkv.permute(2, 0, 3, 1, 4)\n",
"\n",
" # (3, b, num_heads, num_tokens, head_dim) -> 3 times (b, num_heads, num_tokens, head_dim)\n",
" q, k, v = qkv.unbind(0)\n",
" queries, keys, values = qkv.unbind(0)\n",
"\n",
" use_dropout = 0. if not self.training else self.dropout\n",
" context_vec = torch.nn.functional.scaled_dot_product_attention(q, k, v, \n",
" attn_mask=None, dropout_p=use_dropout, is_causal=True)\n",
" context_vec = nn.functional.scaled_dot_product_attention(\n",
" queries, keys, values, attn_mask=None, dropout_p=use_dropout, is_causal=True)\n",
"\n",
" # Combine heads, where self.d_out = self.num_heads * self.head_dim\n",
" context_vec = context_vec.transpose(1, 2).contiguous().view(batch_size, num_tokens, self.d_out)\n",
@ -396,7 +396,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
"version": "3.10.12"
}
},
"nbformat": 4,