mtmd: support MiniCPM-o 4.5(vision only) (#19211)

Signed-off-by: tc-mb <caitianchi@modelbest.cn>
This commit is contained in:
tc-mb 2026-01-31 06:19:30 +08:00 committed by GitHub
parent 1488339138
commit ec6c7421e4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 14 additions and 2 deletions

View File

@ -1005,6 +1005,8 @@ struct clip_model_loader {
hparams.minicpmv_query_num = 64;
} else if (hparams.minicpmv_version == 6) {
hparams.minicpmv_query_num = 64;
} else if (hparams.minicpmv_version == 100045) {
hparams.minicpmv_query_num = 64;
} else {
hparams.minicpmv_query_num = 96;
}
@ -3209,6 +3211,9 @@ int clip_n_output_tokens(const struct clip_ctx * ctx, struct clip_image_f32 * im
} else if (params.minicpmv_version == 6) {
// MiniCPM-V 4.5
n_patches = 64;
} else if (params.minicpmv_version == 100045) {
// MiniCPM-o 4.5
n_patches = 64;
} else {
GGML_ABORT("Unknown minicpmv version");
}

View File

@ -501,7 +501,7 @@ default_image_mean = [0.5, 0.5, 0.5]
default_image_std = [0.5, 0.5, 0.5]
ap.add_argument('--image-mean', type=float, nargs='+', help='Mean of the images for normalization (overrides processor) ', default=None)
ap.add_argument('--image-std', type=float, nargs='+', help='Standard deviation of the images for normalization (overrides processor)', default=None)
ap.add_argument('--minicpmv_version', type=int, help='minicpmv_version: MiniCPM-V-2 use 1; MiniCPM-V-2.5 use 2; MiniCPM-V-2.6 use 3; MiniCPM-o-2.6 use 4; MiniCPM-V 4.0 use 5; MiniCPM-o-4.0 use 6', default=2)
ap.add_argument('--minicpmv_version', type=int, help='minicpmv_version: MiniCPM-V-2 use 1; MiniCPM-V-2.5 use 2; MiniCPM-V-2.6 use 3; MiniCPM-o-2.6 use 4; MiniCPM-V 4.0 use 5; MiniCPM-o-4.0 use 6; MiniCPM-o-4.5 use 100045', default=2)
# with proper
args = ap.parse_args()
@ -610,6 +610,9 @@ else:
elif minicpmv_version == 6:
emb_dim = 4096
block_count = 27
elif minicpmv_version == 100045:
emb_dim = 4096
block_count = 27
default_vision_config = {
"hidden_size": 1152,
@ -637,6 +640,10 @@ elif minicpmv_version == 6:
default_vision_config["model_type"] = "siglip_vision_model"
vision_config = SiglipVisionConfig(**default_vision_config)
model = SiglipVisionTransformer(vision_config)
elif minicpmv_version == 100045:
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

@ -236,7 +236,7 @@ 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 || minicpmv_version == 6) {
} else if (minicpmv_version == 3 || minicpmv_version == 4 || minicpmv_version == 5 || minicpmv_version == 6 || minicpmv_version == 100045) {
// minicpmv 2.6 format:
// <image> (overview) </image><slice> (slice) </slice><slice> (slice) </slice>\n ...
slice_tmpl = MTMD_SLICE_TMPL_MINICPMV_2_6;