|
|
@@ -879,9 +879,15 @@ struct clip_graph {
|
|
|
// add CLS token
|
|
|
inp = ggml_concat(ctx0, inp, model.class_embedding, 1);
|
|
|
|
|
|
+ // The larger models use a different ViT, which uses RMS norm instead of layer norm
|
|
|
+ // ref: https://github.com/ggml-org/llama.cpp/pull/13443#issuecomment-2869786188
|
|
|
+ norm_type norm_t = (hparams.n_embd == 3200 && hparams.n_layer == 45)
|
|
|
+ ? NORM_TYPE_RMS // 6B ViT (Used by InternVL 2.5/3 - 26B, 38B, 78B)
|
|
|
+ : NORM_TYPE_NORMAL; // 300M ViT (Used by all smaller InternVL models)
|
|
|
+
|
|
|
ggml_tensor * cur = build_vit(
|
|
|
inp, n_pos,
|
|
|
- NORM_TYPE_NORMAL,
|
|
|
+ norm_t,
|
|
|
hparams.ffn_op,
|
|
|
model.position_embeddings,
|
|
|
nullptr);
|