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
@@ -41,7 +41,7 @@ bool llama_adapter_cvec::init(const llama_model & model) {
|
||||
auto it = ctx_map.find(buft);
|
||||
if (it == ctx_map.end()) {
|
||||
ggml_init_params params = {
|
||||
/*.mem_size =*/ hparams.n_layer*ggml_tensor_overhead(),
|
||||
/*.mem_size =*/ hparams.n_layer()*ggml_tensor_overhead(),
|
||||
/*.mem_buffer =*/ NULL,
|
||||
/*.no_alloc =*/ true,
|
||||
};
|
||||
@@ -61,9 +61,9 @@ bool llama_adapter_cvec::init(const llama_model & model) {
|
||||
};
|
||||
|
||||
// make tensors
|
||||
tensors.reserve(hparams.n_layer);
|
||||
tensors.reserve(hparams.n_layer());
|
||||
tensors.push_back(nullptr); // there's never a tensor for layer 0
|
||||
for (size_t il = 1; il < hparams.n_layer; il++) {
|
||||
for (size_t il = 1; il < hparams.n_layer(); il++) {
|
||||
ggml_backend_buffer_type_t buft = model.select_buft(il);
|
||||
ggml_context * ctx = ctx_for_buft(buft);
|
||||
if (!ctx) {
|
||||
@@ -121,7 +121,7 @@ bool llama_adapter_cvec::apply(
|
||||
layer_start = il_start;
|
||||
layer_end = il_end;
|
||||
|
||||
for (size_t il = 1; il < hparams.n_layer; il++) {
|
||||
for (size_t il = 1; il < hparams.n_layer(); il++) {
|
||||
assert(tensors[il] != nullptr);
|
||||
|
||||
const size_t off = n_embd * (il - 1); // buffer doesn't have data for layer 0, since it's never present
|
||||
|
||||
Reference in New Issue
Block a user