mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2026-04-11 14:21:41 +08:00
remove redundant context_length in GQA
This commit is contained in:
parent
06ebac3c34
commit
4715dc3be5
@ -233,7 +233,7 @@
|
||||
"source": [
|
||||
"class GroupedQueryAttention(nn.Module):\n",
|
||||
" def __init__(\n",
|
||||
" self, d_in, d_out, context_length, num_heads,\n",
|
||||
" self, d_in, d_out, num_heads,\n",
|
||||
" num_kv_groups,\n",
|
||||
" dtype=None\n",
|
||||
" ):\n",
|
||||
@ -320,7 +320,6 @@
|
||||
" self.att = GroupedQueryAttention(\n",
|
||||
" d_in=cfg[\"emb_dim\"],\n",
|
||||
" d_out=cfg[\"emb_dim\"],\n",
|
||||
" context_length=cfg[\"context_length\"],\n",
|
||||
" num_heads=cfg[\"n_heads\"],\n",
|
||||
" num_kv_groups=cfg[\"n_kv_groups\"],\n",
|
||||
" dtype=cfg[\"dtype\"]\n",
|
||||
|
||||
Loading…
Reference in New Issue
Block a user