tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-15 20:53:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

mtmd : support MiniCPM-V 4.0 (#14983)

Browse Source 
* support minicpm-v 4

* add md

* support MiniCPM-o 4.0

* add default location

* temp rm MiniCPM-o 4.0

* fix code

* fix "minicpmv_projector" default path
This commit is contained in:
tc-mb
2025-07-31 23:22:17 +08:00
committed by GitHub
parent 36e5fe7bcd
commit 952a47f455
8 changed files with 145 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py
View File

@@ -497,11 +497,11 @@ ap.add_argument("--projector-type", help="Type of projector. Possible values: ml
ap.add_argument("-o", "--output-dir", help="Directory to save GGUF files. Default is the original model directory", default=None)
# Example --image_mean 0.48145466 0.4578275 0.40821073 --image_std 0.26862954 0.26130258 0.27577711
# Example --image_mean 0.5 0.5 0.5 --image_std 0.5 0.5 0.5
default_image_mean = [0.48145466, 0.4578275, 0.40821073]
default_image_std = [0.26862954, 0.26130258, 0.27577711]
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', 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', default=2)
# with proper
args = ap.parse_args()
@@ -517,6 +517,17 @@ if args.use_f32:
# output in the same directory as the model if output_dir is None
dir_model = args.model_dir
# If minicpmv_projector is not specified but the default path exists, use the default path
if args.minicpmv_projector is None:
default_projector_path = os.path.join(dir_model, "minicpmv.projector")
if os.path.isfile(default_projector_path):
args.minicpmv_projector = default_projector_path
print(f"Found default projector file: {default_projector_path}")
# If output_dir is not specified, use model_dir as the default value
if args.output_dir is None:
args.output_dir = dir_model
if args.clip_model_is_vision or not os.path.exists(dir_model + "/vocab.json") or args.clip_model_is_openclip:
vocab = None
tokens = None
@@ -546,18 +557,21 @@ if args.use_f32:
minicpmv_version = args.minicpmv_version
emb_dim = 4096
block_count = 26
if minicpmv_version == 1:
if minicpmv_version == 1: # MiniCPM-V 2.0
emb_dim = 2304
block_count = 26
elif minicpmv_version == 2:
elif minicpmv_version == 2: # MiniCPM-V 2.5
emb_dim = 4096
block_count = 27
elif minicpmv_version == 3:
elif minicpmv_version == 3: # MiniCPM-V 2.6
emb_dim = 3584
block_count = 27
elif minicpmv_version == 4:
elif minicpmv_version == 4: # MiniCPM-o 2.6
emb_dim = 3584
block_count = 27
elif minicpmv_version == 5: # MiniCPM-V 4.0
emb_dim = 2560
block_count = 27
default_vision_config = {
"hidden_size": 1152,
@@ -577,6 +591,10 @@ if minicpmv_version == 3:
elif minicpmv_version == 4:
vision_config = SiglipVisionConfig(**default_vision_config)
model = SiglipVisionTransformer(vision_config)
elif minicpmv_version == 5:
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:
@@ -603,7 +621,7 @@ elif args.vision_only:
else:
fname_middle = ""
output_dir = args.output_dir if args.output_dir is not None else dir_model
output_dir = args.output_dir
os.makedirs(output_dir, exist_ok=True)
output_prefix = os.path.basename(output_dir).replace("ggml_", "")
fname_out = os.path.join(output_dir, f"{fname_middle}model-{ftype_str[ftype]}.gguf")