model : support MiniCPM-V 4.5 (#15575)

This commit is contained in:
tc-mb
2025-08-26 16:05:55 +08:00
committed by GitHub
parent 39842a7f73
commit c4e9239064
5 changed files with 61 additions and 2 deletions

View File

@@ -2202,6 +2202,8 @@ struct clip_model_loader {
hparams.minicpmv_query_num = 64;
} else if (hparams.minicpmv_version == 5) {
hparams.minicpmv_query_num = 64;
} else if (hparams.minicpmv_version == 6) {
hparams.minicpmv_query_num = 64;
} else {
hparams.minicpmv_query_num = 96;
}
@@ -3685,6 +3687,9 @@ int clip_n_output_tokens(const struct clip_ctx * ctx, struct clip_image_f32 * im
} else if (params.minicpmv_version == 5) {
// MiniCPM-V 4.0
n_patches = 64;
} else if (params.minicpmv_version == 6) {
// MiniCPM-V 4.5
n_patches = 64;
} else {
GGML_ABORT("Unknown minicpmv version");
}

View File

@@ -607,6 +607,9 @@ else:
elif minicpmv_version == 5:
emb_dim = 2560
block_count = 27
elif minicpmv_version == 6:
emb_dim = 4096
block_count = 27
default_vision_config = {
"hidden_size": 1152,
@@ -630,6 +633,10 @@ elif minicpmv_version == 5:
default_vision_config["model_type"] = "siglip_vision_model"
vision_config = SiglipVisionConfig(**default_vision_config)
model = SiglipVisionTransformer(vision_config)
elif minicpmv_version == 6:
default_vision_config["model_type"] = "siglip_vision_model"
vision_config = SiglipVisionConfig(**default_vision_config)
model = SiglipVisionTransformer(vision_config)
processor = None
# if model.attn_pool is not None:

View File

@@ -207,7 +207,7 @@ struct mtmd_context {
tok_row_end_trail = false; // no trailing end-of-row token
ov_img_first = true;
} else if (minicpmv_version == 3 || minicpmv_version == 4 || minicpmv_version == 5) {
} else if (minicpmv_version == 3 || minicpmv_version == 4 || minicpmv_version == 5 || minicpmv_version == 6) {
// minicpmv 2.6 format:
// <image> (overview) </image><slice> (slice) </slice><slice> (slice) </slice>\n ...
slice_tmpl = MTMD_SLICE_TMPL_MINICPMV_2_6;