mtmd, model : merge HunyuanOCR into HunyuanVL and fix OCR vision precision (#23329)

- HunyuanOCR shares the same HF arch and vision layout as HunyuanVL butwas split into a separate path that skipped the +0.1 bilinear sampler used by the HF reference. - Collapse OCR into the HUNYUANVL projector + HUNYUAN_VL text arch
2026-05-21 00:35:37 +02:00
parent 3a479c9132
commit 6a257d4463
15 changed files with 58 additions and 134 deletions
@@ -493,7 +493,6 @@ struct mtmd_context {
                    img_end = "\n"; // prevent empty batch on llama-server
                    image_preproc = std::make_unique<mtmd_image_preprocessor_deepseekocr>(ctx_v);
                } break;
-            case PROJECTOR_TYPE_HUNYUANOCR:
            case PROJECTOR_TYPE_HUNYUANVL:
                {
                    // note: these use fullwidth ｜ (U+FF5C) and ▁ (U+2581) to match the tokenizer vocabulary