model : add support for talkie-1930-13b (#22596)

* initial talkie support, coherent

* reorder to follow convention

* absorb inverse rope

* stop folding scalars to improve quantization

* use broadcasting instead of duplication

* style cleanup

* add scaling support to LoraTorchTensor; use that path in conversion

* use layer_out_scale instead of embd_skip_scale

src/llama-model.cpp

@@ -44,6 +44,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
             return new llama_model_llama_embed(params);
         case LLM_ARCH_MAINCODER:
             return new llama_model_maincoder(params);
+        case LLM_ARCH_TALKIE:
+            return new llama_model_talkie(params);
         case LLM_ARCH_DECI:
             return new llama_model_deci(params);
         case LLM_ARCH_BAICHUAN:
@@ -2353,6 +2355,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
         case LLM_ARCH_QWEN3NEXT:
         case LLM_ARCH_MIMO2:
         case LLM_ARCH_STEP35:
+        case LLM_ARCH_TALKIE:
             return LLAMA_ROPE_TYPE_NEOX;
 
         case LLM_ARCH_QWEN2VL: