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>

This commit is contained in:

Junwon Hwang

2026-06-01 11:48:53 +02:00

committed by

GitHub

co-authored by

LG-AI-EXAONE

parent 19620004f5

commit 48b88c3b00

11 changed files with 356 additions and 16 deletions

									
										tools/mtmd/CMakeLists.txt
									
		+1
		
												View File
												
				@@ -18,6 +18,7 @@ add_library(mtmd

				            models/cogvlm.cpp

				            models/conformer.cpp

				            models/dotsocr.cpp

				            models/exaone4_5.cpp

				            models/gemma4a.cpp

				            models/gemma4v.cpp

				            models/glm4v.cpp