Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/llama-model.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -7457,7 +7457,7 @@ ggml_cgraph * llama_model::build_graph(const llm_graph_params & params) const {
} break;
case LLM_ARCH_MODERN_BERT:
{
llm = std::make_unique<llm_build_modern_bert<true>>(*this, params);
llm = std::make_unique<llm_build_modern_bert>(*this, params);
} break;
case LLM_ARCH_NEO_BERT:
{
Expand Down
1 change: 0 additions & 1 deletion src/models/models.h
Original file line number Diff line number Diff line change
Expand Up @@ -332,7 +332,6 @@ struct llm_build_mistral3 : public llm_graph_context {
llm_build_mistral3(const llama_model & model, const llm_graph_params & params);
};

template <bool iswa>
struct llm_build_modern_bert : public llm_graph_context {
llm_build_modern_bert(const llama_model & model, const llm_graph_params & params);
};
Expand Down
15 changes: 2 additions & 13 deletions src/models/modern-bert.cpp
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
#include "models.h"

template <bool iswa>
llm_build_modern_bert<iswa>::llm_build_modern_bert(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
llm_build_modern_bert::llm_build_modern_bert(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
const int64_t n_embd_head = hparams.n_embd_head_v;
const int64_t n_embd_gqa = hparams.n_embd_v_gqa();

Expand All @@ -24,13 +23,7 @@ llm_build_modern_bert<iswa>::llm_build_modern_bert(const llama_model & model, co
auto * inp_attn = build_attn_inp_no_cache();

for (int il = 0; il < n_layer; ++il) {
float freq_base_l = 0.0f;

if constexpr (iswa) {
freq_base_l = model.get_rope_freq_base(cparams, il);
} else {
freq_base_l = freq_base;
}
float freq_base_l = model.get_rope_freq_base(cparams, il);

cur = inpL;

Expand Down Expand Up @@ -120,7 +113,3 @@ llm_build_modern_bert<iswa>::llm_build_modern_bert(const llama_model & model, co
res->t_embd = cur;
ggml_build_forward_expand(gf, cur);
}

// Explicit template instantiations
template struct llm_build_modern_bert<false>;
template struct llm_build_modern_bert<true>;
Loading