Merge plamo2 changes from master

Author: pwilkin

src/models/plamo2.cpp

@@ -1,8 +1,5 @@
 #include "models.h"
 
-
-
-
 llm_build_plamo2::llm_build_plamo2(const llama_model & model, const llm_graph_params & params) :
     llm_graph_context_mamba(params) {
     ggml_tensor * cur;
@@ -78,6 +75,8 @@ llm_build_plamo2::llm_build_plamo2(const llama_model & model, const llm_graph_pa
     cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);
     cb(cur, "result_norm", -1);
 
+    res->t_embd = cur;
+
     // lm_head
     cur = build_lora_mm(model.output, cur);
     cb(cur, "result_output", -1);