chore : fix models indent after refactor (#16992)

src/models/grok.cpp

@@ -27,7 +27,6 @@ llm_build_grok::llm_build_grok(const llama_model & model, const llm_graph_params
                 LLM_NORM_RMS, il);
         cb(cur, "attn_norm", il);
 
-
         // self-attention
         {
             // compute Q and K and RoPE them

src/models/internlm2.cpp

@@ -1,6 +1,5 @@
 #include "models.h"
 
-
 llm_build_internlm2::llm_build_internlm2(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
     const int64_t n_embd_head = hparams.n_embd_head_v;
 

src/models/jamba.cpp

@@ -1,6 +1,5 @@
 #include "models.h"
 
-
 llm_build_jamba::llm_build_jamba(const llama_model & model, const llm_graph_params & params) : llm_graph_context_mamba(params) {
     const int64_t n_embd_head = hparams.n_embd_head_v;
 

src/models/llada-moe.cpp

@@ -120,4 +120,3 @@ llm_build_llada_moe::llm_build_llada_moe(const llama_model & model, const llm_gr
 
     ggml_build_forward_expand(gf, cur);
 }
-

src/models/llada.cpp

@@ -1,8 +1,6 @@
 #include "models.h"
 
-
-llm_build_llada::llm_build_llada(const llama_model & model, const llm_graph_params & params) :
-        llm_graph_context(params) {
+llm_build_llada::llm_build_llada(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
     // LLaDA is similar to LLaMA but uses non-causal attention for diffusion
     const int64_t n_embd_head = hparams.n_embd_head_v;
 

src/models/llama.cpp

@@ -1,6 +1,5 @@
 #include "models.h"
 
-
 llm_build_llama::llm_build_llama(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
     const int64_t n_embd_head = hparams.n_embd_head_v;
 
@@ -153,4 +152,4 @@ llm_build_llama::llm_build_llama(const llama_model & model, const llm_graph_para
     res->t_logits = cur;
 
     ggml_build_forward_expand(gf, cur);
-    }
+}

src/models/minicpm3.cpp

@@ -1,6 +1,5 @@
 #include "models.h"
 
-
 llm_build_minicpm3::llm_build_minicpm3(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
     //TODO: if the model varies, these parameters need to be read from the model
     const int64_t n_embd_base = 256;

src/models/olmo2.cpp

@@ -1,6 +1,5 @@
 #include "models.h"
 
-
 template <bool iswa>
 llm_build_olmo2<iswa>::llm_build_olmo2(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
     const int64_t n_embd_head = hparams.n_embd_head_v;
@@ -144,7 +143,7 @@ llm_build_olmo2<iswa>::llm_build_olmo2(const llama_model & model, const llm_grap
     res->t_logits = cur;
 
     ggml_build_forward_expand(gf, cur);
-    }
+}
 
 // Explicit template instantiations
 template struct llm_build_olmo2<false>;

src/models/phi3.cpp

@@ -1,6 +1,5 @@
 #include "models.h"
 
-
 template<bool iswa>
 llm_build_phi3<iswa>::llm_build_phi3(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
     const int64_t n_embd_head = hparams.n_embd_head_v;
@@ -146,7 +145,7 @@ llm_build_phi3<iswa>::llm_build_phi3(const llama_model & model, const llm_graph_
     res->t_logits = cur;
 
     ggml_build_forward_expand(gf, cur);
-    }
+}
 
 // Explicit template instantiations
 template struct llm_build_phi3<false>;

src/models/qwen2.cpp

@@ -1,6 +1,5 @@
 #include "models.h"
 
-
 llm_build_qwen2::llm_build_qwen2(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
     const int64_t n_embd_head = hparams.n_embd_head_v;
 

src/models/smallthinker.cpp

@@ -113,7 +113,7 @@ llm_build_smallthinker<iswa>::llm_build_smallthinker(const llama_model & model,
     res->t_logits = cur;
 
     ggml_build_forward_expand(gf, cur);
-    }
+}
 
 // Explicit template instantiations
 template struct llm_build_smallthinker<false>;