hparams : refactor hparams.n_layer (#24060)
* hparams : refactor hparams.n_layer * cont : remove `n_layer_kv()`, use n_layer_all instead * cont : type consistency * pi : update SYSTEM.md * models : fix Step3.5 MTP * cont : remove duplicate switch cases * cont : explicitly set `false` to extra layers for `is_swa` and `is_recr` * cont : fix nextn layer count handling Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
co-authored by
Sigbjørn Skjæret
parent
3ecfb150a4
commit
7acb4e8cd2
+1
-1
@@ -1005,7 +1005,7 @@ llm_graph_context::llm_graph_context(const llm_graph_params & params) :
|
||||
cparams (params.cparams),
|
||||
ubatch (params.ubatch),
|
||||
n_embd (hparams.n_embd),
|
||||
n_layer (hparams.n_layer),
|
||||
n_layer (hparams.n_layer()),
|
||||
n_rot (hparams.n_rot()),
|
||||
n_ctx (cparams.n_ctx),
|
||||
n_head (hparams.n_head()),
|
||||
|
||||
Reference in New Issue
Block a user