Michael Yang df4b146c49 fix: mllama quality (#10807) ... * fix mllama convert - transform attn_gate and ffn_gate - swap attention heads for vision models * fix mllama the mlp gate which was applied in the wrong place		2025-12-29 06:38:05 -06:00
..
model.go	model: handle multiple eos tokens (#10577)	2025-12-29 06:38:01 -06:00
model_text.go	ml: add more rope options (#10775)	2025-12-29 06:38:03 -06:00
model_vision.go	fix: mllama quality (#10807)	2025-12-29 06:38:05 -06:00
process_image.go	chore: update mllama to use ollama engine (#10637)	2025-12-29 06:37:59 -06:00
process_image_test.go	chore: update mllama to use ollama engine (#10637)	2025-12-29 06:37:59 -06:00