model: Add EXAONE 4.5 implementations (#21733)

* Add EXAONE 4.5 and Add GQA for MMproj * mtmd: EXAONE 4.5 vision markers and projector path EXAONE 4.5 uses <vision> and </vision> for image boundaries; Qwen keeps <|vision_start|> and <|vision_end|>. Route EXAONE 4.5 through the Qwen2.5-VL-style encode path (window attention pattern, optional mmproj input norm). Update exaone4_5 projector weights and convert_hf_to_gguf for mmproj export. * mtmd: load EXAONE4 nextn tensors correctly Align EXAONE4 tensor registration with EXAONE_MOE for NextN/MTP slots and avoid skip-flag propagation on duplicated rope_freqs so model loading succeeds for EXAONE 4.5 GGUF. * Minor fixes * Address PR feedback * Address PR feedback * Fix EXAONE after merge * Fix EXAONE 4.5 conversion * Address PR feedback * Refactor EXAONE 4.5 conversion * Address PR feedback * Fix unintended deletion * Minor fix --------- Co-authored-by: LG-AI-EXAONE <exaonemodels@lgresearch.ai>
2026-06-01 11:48:53 +02:00
parent 19620004f5
commit 48b88c3b00
11 changed files with 356 additions and 16 deletions
@@ -505,6 +505,13 @@ struct mtmd_context {
                    img_end = "<｜hy_place▁holder▁no▁101｜>";
                    image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
                } break;
+            case PROJECTOR_TYPE_EXAONE4_5:
+                {
+                    // <vision> ... (image embeddings) ... </vision>
+                    img_beg = "<vision>";
+                    img_end = "</vision>";
+                    image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
+                } break;
            default:
                throw std::runtime_error(string_format("%s: unexpected vision projector type %d\n", __func__, proj));
        }