Commit 90f071c6 authored by Michael Yang's avatar Michael Yang
Browse files

default head_kv to 1

parent a039e383
......@@ -148,15 +148,15 @@ func (kv KV) HeadCount() uint64 {
}
func (kv KV) HeadCountKV() uint64 {
return kv.u64(fmt.Sprintf("%s.attention.head_count_kv", kv.Architecture()))
if headCountKV := kv.u64(fmt.Sprintf("%s.attention.head_count_kv", kv.Architecture())); headCountKV > 0 {
return headCountKV
}
return 1
}
func (kv KV) GQA() uint64 {
if headCountKV := kv.HeadCountKV(); headCountKV > 0 {
return kv.HeadCount() / headCountKV
}
return 0
return kv.HeadCount() / kv.HeadCountKV()
}
func (kv KV) EmbeddingLength() uint64 {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment