Remove unused field, update script path in docs.

Author: lzhang

docs/multimodal/minicpmo2.6.md

@@ -13,7 +13,7 @@ If there are differences in usage, please refer to the official build [documenta
 
 Clone llama.cpp:
 ```bash
-git clone https://github.com/ggerganov/llama.cpp
+git clone https://github.com/ggml-org/llama.cpp
 cd llama.cpp
 ```
 
@@ -29,8 +29,8 @@ cmake --build build --config Release
 Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-o-2_6-gguf) by us)
 
 ```bash
-python ./tools/mtmd/minicpmv-surgery.py -m ../MiniCPM-o-2_6
-python ./tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-o-2_6 --minicpmv-projector ../MiniCPM-o-2_6/minicpmv.projector --output-dir ../MiniCPM-o-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 4
+python ./tools/mtmd/legacy-models/minicpmv-surgery.py -m ../MiniCPM-o-2_6
+python ./tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-o-2_6 --minicpmv-projector ../MiniCPM-o-2_6/minicpmv.projector --output-dir ../MiniCPM-o-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 4
 python ./convert_hf_to_gguf.py ../MiniCPM-o-2_6/model
 
 # quantize int4 version

docs/multimodal/minicpmv2.5.md

@@ -28,8 +28,8 @@ cmake --build build --config Release
 Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf) by us)
 
 ```bash
-python ./tools/mtmd/minicpmv-surgery.py -m ../MiniCPM-Llama3-V-2_5
-python ./tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-Llama3-V-2_5 --minicpmv-projector ../MiniCPM-Llama3-V-2_5/minicpmv.projector --output-dir ../MiniCPM-Llama3-V-2_5/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 2
+python ./tools/mtmd/legacy-models/minicpmv-surgery.py -m ../MiniCPM-Llama3-V-2_5
+python ./tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-Llama3-V-2_5 --minicpmv-projector ../MiniCPM-Llama3-V-2_5/minicpmv.projector --output-dir ../MiniCPM-Llama3-V-2_5/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 2
 python ./convert_hf_to_gguf.py ../MiniCPM-Llama3-V-2_5/model
 
 # quantize int4 version

docs/multimodal/minicpmv2.6.md

@@ -12,7 +12,7 @@ If there are differences in usage, please refer to the official build [documenta
 
 Clone llama.cpp:
 ```bash
-git clone https://github.com/ggerganov/llama.cpp
+git clone https://github.com/ggml-org/llama.cpp
 cd llama.cpp
 ```
 
@@ -28,8 +28,8 @@ cmake --build build --config Release
 Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-V-2_6-gguf) by us)
 
 ```bash
-python ./tools/mtmd/minicpmv-surgery.py -m ../MiniCPM-V-2_6
-python ./tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-V-2_6 --minicpmv-projector ../MiniCPM-V-2_6/minicpmv.projector --output-dir ../MiniCPM-V-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 3
+python ./tools/mtmd/legacy-models/minicpmv-surgery.py -m ../MiniCPM-V-2_6
+python ./tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-V-2_6 --minicpmv-projector ../MiniCPM-V-2_6/minicpmv.projector --output-dir ../MiniCPM-V-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 3
 python ./convert_hf_to_gguf.py ../MiniCPM-V-2_6/model
 
 # quantize int4 version

tools/mtmd/clip-impl.h

@@ -45,7 +45,6 @@
 #define KEY_ATTN_WINDOW_SIZE      "clip.vision.window_size"
 #define KEY_MINICPMV_VERSION      "clip.minicpmv_version"
 #define KEY_MINICPMV_QUERY_NUM    "clip.minicpmv_query_num"
-#define KEY_MINICPMV_PROJ_DIM     "clip.minicpmv_projection_dim"
 
 // audio-specific
 #define KEY_A_NUM_MEL_BINS      "clip.audio.num_mel_bins"

tools/mtmd/clip.cpp

@@ -202,7 +202,6 @@ struct clip_hparams {
     bool has_llava_projector = false;
     int minicpmv_version = 0;
     int32_t minicpmv_query_num = 0;         // MiniCPM-V query number
-    int32_t minicpmv_projection_dim = 0;    // MiniCPM-V projection dimension
 };
 
 struct clip_layer {
@@ -2106,7 +2105,6 @@ struct clip_model_loader {
                 get_u32(KEY_IMAGE_CROP_RESOLUTION, hparams.image_crop_resolution, false);
                 get_i32(KEY_MINICPMV_VERSION, hparams.minicpmv_version, false); // legacy
                 get_u32(KEY_MINICPMV_QUERY_NUM, hparams.minicpmv_query_num, false);
-                get_u32(KEY_MINICPMV_PROJ_DIM, hparams.minicpmv_projection_dim, false);
                 if (hparams.minicpmv_query_num == 0) {
                     // Fallback to hardcoded values for legacy models
                     if (hparams.minicpmv_version == 3) {

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

@@ -520,7 +520,7 @@ def bytes_to_unicode():
 # Read config.json to get actual model configuration
 config_path = os.path.join(dir_model, "config.json")
 model_config = {}
-if os.path.exists(config_path):
+if os.path.isfile(config_path):
     with open(config_path, "r", encoding="utf-8") as f:
         model_config = json.load(f)
     print(f"Loaded config from {config_path}")
@@ -681,7 +681,6 @@ def bytes_to_unicode():
     query_num = model_config.get("query_num", 0) if model_config else 0
     resampler_emb_dim = model_config.get("hidden_size", 0) if model_config else 0
     fout.add_uint32("clip.minicpmv_query_num", query_num)
-    fout.add_uint32("clip.minicpmv_projection_dim", resampler_emb_dim)
 
     if processor is not None:
         image_mean = processor.image_processor.image_mean if args.image_mean is None or args.image_mean == default_image_mean else args.image_mean