Merge 0bec4f6b4d into d7b31a9d84
This commit is contained in:
tc-mb
GitHub
commit
2e09d70548
6 changed files with 80 additions and 175 deletions
|
|
@ -5,13 +5,25 @@ Currently, this readme only supports minicpm-omni's image capabilities, and we w
|
|||
|
||||
Download [MiniCPM-o-2_6](https://huggingface.co/openbmb/MiniCPM-o-2_6) PyTorch model from huggingface to "MiniCPM-o-2_6" folder.
|
||||
|
||||
|
||||
### Build llama.cpp
|
||||
Readme modification time: 20250206
|
||||
|
||||
If there are differences in usage, please refer to the official build [documentation](https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md)
|
||||
|
||||
Clone llama.cpp:
|
||||
```bash
|
||||
git clone git@github.com:OpenBMB/llama.cpp.git
|
||||
git clone https://github.com/ggerganov/llama.cpp
|
||||
cd llama.cpp
|
||||
git checkout minicpm-omni
|
||||
```
|
||||
|
||||
Build llama.cpp using `CMake`:
|
||||
```bash
|
||||
cmake -B build
|
||||
cmake --build build --config Release
|
||||
```
|
||||
|
||||
|
||||
### Usage of MiniCPM-o 2.6
|
||||
|
||||
Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-o-2_6-gguf) by us)
|
||||
|
|
@ -22,25 +34,15 @@ python ./examples/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-
|
|||
python ./convert_hf_to_gguf.py ../MiniCPM-o-2_6/model
|
||||
|
||||
# quantize int4 version
|
||||
./llama-quantize ../MiniCPM-o-2_6/model/ggml-model-f16.gguf ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf Q4_K_M
|
||||
./build/bin/llama-quantize ../MiniCPM-o-2_6/model/ggml-model-f16.gguf ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf Q4_K_M
|
||||
```
|
||||
|
||||
Build llama.cpp using `CMake`:
|
||||
https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md
|
||||
|
||||
```bash
|
||||
cmake -B build
|
||||
cmake --build build --config Release
|
||||
```
|
||||
|
||||
Inference on Linux or Mac
|
||||
```
|
||||
```bash
|
||||
# run f16 version
|
||||
./llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-f16.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
./build/bin/llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-f16.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
|
||||
# run quantized int4 version
|
||||
./llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
|
||||
# or run in interactive mode
|
||||
./llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -i
|
||||
./build/bin/llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
```
|
||||
|
|
|
|||
|
|
@ -4,13 +4,26 @@
|
|||
|
||||
Download [MiniCPM-Llama3-V-2_5](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5) PyTorch model from huggingface to "MiniCPM-Llama3-V-2_5" folder.
|
||||
|
||||
|
||||
### Build llama.cpp
|
||||
Readme modification time: 20250206
|
||||
|
||||
If there are differences in usage, please refer to the official build [documentation](https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md)
|
||||
|
||||
Clone llama.cpp:
|
||||
```bash
|
||||
git clone https://github.com/ggerganov/llama.cpp
|
||||
cd llama.cpp
|
||||
```
|
||||
|
||||
### Usage
|
||||
Build llama.cpp using `CMake`:
|
||||
```bash
|
||||
cmake -B build
|
||||
cmake --build build --config Release
|
||||
```
|
||||
|
||||
|
||||
### Usage of MiniCPM-Llama3-V 2.5
|
||||
|
||||
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)
|
||||
|
||||
|
|
@ -20,80 +33,15 @@ python ./examples/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-
|
|||
python ./convert_hf_to_gguf.py ../MiniCPM-Llama3-V-2_5/model
|
||||
|
||||
# quantize int4 version
|
||||
./llama-quantize ../MiniCPM-Llama3-V-2_5/model/model-8B-F16.gguf ../MiniCPM-Llama3-V-2_5/model/ggml-model-Q4_K_M.gguf Q4_K_M
|
||||
./build/bin/llama-quantize ../MiniCPM-Llama3-V-2_5/model/model-8B-F16.gguf ../MiniCPM-Llama3-V-2_5/model/ggml-model-Q4_K_M.gguf Q4_K_M
|
||||
```
|
||||
|
||||
Build for Linux or Mac
|
||||
|
||||
```bash
|
||||
make
|
||||
make llama-minicpmv-cli
|
||||
```
|
||||
|
||||
Inference on Linux or Mac
|
||||
```
|
||||
```bash
|
||||
# run f16 version
|
||||
./llama-minicpmv-cli -m ../MiniCPM-Llama3-V-2_5/model/model-8B-F16.gguf --mmproj ../MiniCPM-Llama3-V-2_5/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
./build/bin/llama-minicpmv-cli -m ../MiniCPM-Llama3-V-2_5/model/model-8B-F16.gguf --mmproj ../MiniCPM-Llama3-V-2_5/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
|
||||
# run quantized int4 version
|
||||
./llama-minicpmv-cli -m ../MiniCPM-Llama3-V-2_5/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-Llama3-V-2_5/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
|
||||
# or run in interactive mode
|
||||
./llama-minicpmv-cli -m ../MiniCPM-Llama3-V-2_5/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-Llama3-V-2_5/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -i
|
||||
```
|
||||
|
||||
### Android
|
||||
|
||||
#### Build on Android device using Termux
|
||||
We found that build on Android device would bring better runtime performance, so we recommend to build on device.
|
||||
|
||||
[Termux](https://github.com/termux/termux-app#installation) is a terminal app on Android device (no root required).
|
||||
|
||||
Install tools in Termux:
|
||||
```
|
||||
apt update && apt upgrade -y
|
||||
apt install git make cmake
|
||||
```
|
||||
|
||||
It's recommended to move your model inside the `~/` directory for best performance:
|
||||
```
|
||||
cd storage/downloads
|
||||
mv model.gguf ~/
|
||||
```
|
||||
|
||||
#### Building the Project using Android NDK
|
||||
Obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake.
|
||||
|
||||
Execute the following commands on your computer to avoid downloading the NDK to your mobile. Alternatively, you can also do this in Termux:
|
||||
|
||||
```bash
|
||||
mkdir build-android
|
||||
cd build-android
|
||||
export NDK=/your_ndk_path
|
||||
cmake -DCMAKE_TOOLCHAIN_FILE=$NDK/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=android-23 -DCMAKE_C_FLAGS=-march=armv8.4a+dotprod ..
|
||||
make
|
||||
```
|
||||
|
||||
Install [termux](https://github.com/termux/termux-app#installation) on your device and run `termux-setup-storage` to get access to your SD card (if Android 11+ then run the command twice).
|
||||
|
||||
Finally, copy these built `llama` binaries and the model file to your device storage. Because the file permissions in the Android sdcard cannot be changed, you can copy the executable files to the `/data/data/com.termux/files/home/bin` path, and then execute the following commands in Termux to add executable permission:
|
||||
|
||||
(Assumed that you have pushed the built executable files to the /sdcard/llama.cpp/bin path using `adb push`)
|
||||
```
|
||||
$cp -r /sdcard/llama.cpp/bin /data/data/com.termux/files/home/
|
||||
$cd /data/data/com.termux/files/home/bin
|
||||
$chmod +x ./*
|
||||
```
|
||||
|
||||
Download models and push them to `/sdcard/llama.cpp/`, then move it to `/data/data/com.termux/files/home/model/`
|
||||
|
||||
```
|
||||
$mv /sdcard/llama.cpp/ggml-model-Q4_K_M.gguf /data/data/com.termux/files/home/model/
|
||||
$mv /sdcard/llama.cpp/mmproj-model-f16.gguf /data/data/com.termux/files/home/model/
|
||||
```
|
||||
|
||||
Now, you can start chatting:
|
||||
```
|
||||
$cd /data/data/com.termux/files/home/bin
|
||||
$./llama-minicpmv-cli -m ../model/ggml-model-Q4_K_M.gguf --mmproj ../model/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
./build/bin/llama-minicpmv-cli -m ../MiniCPM-Llama3-V-2_5/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-Llama3-V-2_5/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
```
|
||||
|
|
|
|||
|
|
@ -4,13 +4,25 @@
|
|||
|
||||
Download [MiniCPM-V-2_6](https://huggingface.co/openbmb/MiniCPM-V-2_6) PyTorch model from huggingface to "MiniCPM-V-2_6" folder.
|
||||
|
||||
|
||||
### Build llama.cpp
|
||||
Readme modification time: 20250206
|
||||
|
||||
If there are differences in usage, please refer to the official build [documentation](https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md)
|
||||
|
||||
Clone llama.cpp:
|
||||
```bash
|
||||
git clone git@github.com:OpenBMB/llama.cpp.git
|
||||
git clone https://github.com/ggerganov/llama.cpp
|
||||
cd llama.cpp
|
||||
git checkout minicpmv-main
|
||||
```
|
||||
|
||||
Build llama.cpp using `CMake`:
|
||||
```bash
|
||||
cmake -B build
|
||||
cmake --build build --config Release
|
||||
```
|
||||
|
||||
|
||||
### Usage of MiniCPM-V 2.6
|
||||
|
||||
Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-V-2_6-gguf) by us)
|
||||
|
|
@ -21,87 +33,15 @@ python ./examples/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-
|
|||
python ./convert_hf_to_gguf.py ../MiniCPM-V-2_6/model
|
||||
|
||||
# quantize int4 version
|
||||
./llama-quantize ../MiniCPM-V-2_6/model/ggml-model-f16.gguf ../MiniCPM-V-2_6/model/ggml-model-Q4_K_M.gguf Q4_K_M
|
||||
./build/bin/llama-quantize ../MiniCPM-V-2_6/model/ggml-model-f16.gguf ../MiniCPM-V-2_6/model/ggml-model-Q4_K_M.gguf Q4_K_M
|
||||
```
|
||||
|
||||
Build for Linux or Mac
|
||||
|
||||
```bash
|
||||
make
|
||||
make llama-minicpmv-cli
|
||||
```
|
||||
|
||||
Inference on Linux or Mac
|
||||
```
|
||||
```bash
|
||||
# run f16 version
|
||||
./llama-minicpmv-cli -m ../MiniCPM-V-2_6/model/ggml-model-f16.gguf --mmproj ../MiniCPM-V-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
./build/bin/llama-minicpmv-cli -m ../MiniCPM-V-2_6/model/ggml-model-f16.gguf --mmproj ../MiniCPM-V-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
|
||||
# run quantized int4 version
|
||||
./llama-minicpmv-cli -m ../MiniCPM-V-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-V-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
|
||||
# or run in interactive mode
|
||||
./llama-minicpmv-cli -m ../MiniCPM-V-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-V-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -i
|
||||
```
|
||||
|
||||
### Video
|
||||
Install FFmpeg
|
||||
```
|
||||
brew install ffmpeg
|
||||
brew install pkg-config
|
||||
```
|
||||
|
||||
### Android
|
||||
|
||||
#### Build on Android device using Termux
|
||||
We found that build on Android device would bring better runtime performance, so we recommend to build on device.
|
||||
|
||||
[Termux](https://github.com/termux/termux-app#installation) is a terminal app on Android device (no root required).
|
||||
|
||||
Install tools in Termux:
|
||||
```
|
||||
apt update && apt upgrade -y
|
||||
apt install git make cmake
|
||||
```
|
||||
|
||||
It's recommended to move your model inside the `~/` directory for best performance:
|
||||
```
|
||||
cd storage/downloads
|
||||
mv model.gguf ~/
|
||||
```
|
||||
|
||||
#### Building the Project using Android NDK
|
||||
Obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake.
|
||||
|
||||
Execute the following commands on your computer to avoid downloading the NDK to your mobile. Alternatively, you can also do this in Termux:
|
||||
|
||||
```bash
|
||||
mkdir build-android
|
||||
cd build-android
|
||||
export NDK=/your_ndk_path
|
||||
cmake -DCMAKE_TOOLCHAIN_FILE=$NDK/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=android-23 -DCMAKE_C_FLAGS=-march=armv8.4a+dotprod ..
|
||||
make
|
||||
```
|
||||
|
||||
Install [termux](https://github.com/termux/termux-app#installation) on your device and run `termux-setup-storage` to get access to your SD card (if Android 11+ then run the command twice).
|
||||
|
||||
Finally, copy these built `llama` binaries and the model file to your device storage. Because the file permissions in the Android sdcard cannot be changed, you can copy the executable files to the `/data/data/com.termux/files/home/bin` path, and then execute the following commands in Termux to add executable permission:
|
||||
|
||||
(Assumed that you have pushed the built executable files to the /sdcard/llama.cpp/bin path using `adb push`)
|
||||
```
|
||||
$cp -r /sdcard/llama.cpp/bin /data/data/com.termux/files/home/
|
||||
$cd /data/data/com.termux/files/home/bin
|
||||
$chmod +x ./*
|
||||
```
|
||||
|
||||
Download models and push them to `/sdcard/llama.cpp/`, then move it to `/data/data/com.termux/files/home/model/`
|
||||
|
||||
```
|
||||
$mv /sdcard/llama.cpp/ggml-model-Q4_K_M.gguf /data/data/com.termux/files/home/model/
|
||||
$mv /sdcard/llama.cpp/mmproj-model-f16.gguf /data/data/com.termux/files/home/model/
|
||||
```
|
||||
|
||||
Now, you can start chatting:
|
||||
```
|
||||
$cd /data/data/com.termux/files/home/bin
|
||||
$./llama-minicpmv-cli -m ../model/ggml-model-Q4_K_M.gguf --mmproj ../model/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
./build/bin/llama-minicpmv-cli -m ../MiniCPM-V-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-V-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1357,6 +1357,7 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
|
|||
LOG_INF("%s: vision_encoder: %d\n", __func__, new_clip->has_vision_encoder);
|
||||
LOG_INF("%s: llava_projector: %d\n", __func__, new_clip->has_llava_projector);
|
||||
LOG_INF("%s: minicpmv_projector: %d\n", __func__, new_clip->has_minicpmv_projector);
|
||||
LOG_INF("%s: minicpmv_version: %d\n", __func__, new_clip->minicpmv_version);
|
||||
LOG_INF("%s: glm_projector: %d\n", __func__, new_clip->has_glm_projector);
|
||||
LOG_INF("%s: model size: %.2f MB\n", __func__, model_size / 1024.0 / 1024.0);
|
||||
LOG_INF("%s: metadata size: %.2f MB\n", __func__, ggml_get_mem_size(meta) / 1024.0 / 1024.0);
|
||||
|
|
|
|||
|
|
@ -148,19 +148,34 @@ static void process_image(struct llava_context * ctx_llava, struct llava_image_e
|
|||
process_eval_image_embed(ctx_llava, embeds, params->n_batch, &n_past, idx++);
|
||||
eval_string(ctx_llava->ctx_llama, std::string("</image>").c_str(), params->n_batch, &n_past, false);
|
||||
if (num_image_embeds > 1) {
|
||||
size_t num_image_embeds_col = clip_uhd_num_image_embeds_col(ctx_llava->ctx_clip);
|
||||
eval_string(ctx_llava->ctx_llama, std::string("<slice>").c_str(), params->n_batch, &n_past, false);
|
||||
for (size_t i = 0; i < (num_image_embeds-1)/num_image_embeds_col; ++i) {
|
||||
for (size_t j = 0; j < num_image_embeds_col; ++j) {
|
||||
eval_string(ctx_llava->ctx_llama, std::string("<image>").c_str(), params->n_batch, &n_past, false);
|
||||
process_eval_image_embed(ctx_llava, embeds, params->n_batch, &n_past, idx++);
|
||||
eval_string(ctx_llava->ctx_llama, std::string("</image>").c_str(), params->n_batch, &n_past, false);
|
||||
if (j == num_image_embeds_col - 1) {
|
||||
eval_string(ctx_llava->ctx_llama, std::string("\n").c_str(), params->n_batch, &n_past, false);
|
||||
if (has_minicpmv_projector == 2) {
|
||||
size_t num_image_embeds_col = clip_uhd_num_image_embeds_col(ctx_llava->ctx_clip);
|
||||
eval_string(ctx_llava->ctx_llama, std::string("<slice>").c_str(), params->n_batch, &n_past, false);
|
||||
for (size_t i = 0; i < (num_image_embeds-1)/num_image_embeds_col; ++i) {
|
||||
for (size_t j = 0; j < num_image_embeds_col; ++j) {
|
||||
eval_string(ctx_llava->ctx_llama, std::string("<image>").c_str(), params->n_batch, &n_past, false);
|
||||
process_eval_image_embed(ctx_llava, embeds, params->n_batch, &n_past, idx++);
|
||||
eval_string(ctx_llava->ctx_llama, std::string("</image>").c_str(), params->n_batch, &n_past, false);
|
||||
if (j == num_image_embeds_col - 1) {
|
||||
eval_string(ctx_llava->ctx_llama, std::string("\n").c_str(), params->n_batch, &n_past, false);
|
||||
}
|
||||
}
|
||||
}
|
||||
eval_string(ctx_llava->ctx_llama, std::string("</slice>").c_str(), params->n_batch, &n_past, false);
|
||||
}
|
||||
else if (has_minicpmv_projector == 3 || has_minicpmv_projector == 4) {
|
||||
size_t num_image_embeds_col = clip_uhd_num_image_embeds_col(ctx_llava->ctx_clip);
|
||||
for (size_t i = 0; i < (num_image_embeds-1)/num_image_embeds_col; ++i) {
|
||||
for (size_t j = 0; j < num_image_embeds_col; ++j) {
|
||||
eval_string(ctx_llava->ctx_llama, std::string("<slice>").c_str(), params->n_batch, &n_past, false);
|
||||
process_eval_image_embed(ctx_llava, embeds, params->n_batch, &n_past, idx++);
|
||||
eval_string(ctx_llava->ctx_llama, std::string("</slice>").c_str(), params->n_batch, &n_past, false);
|
||||
if (j == num_image_embeds_col - 1) {
|
||||
eval_string(ctx_llava->ctx_llama, std::string("\n").c_str(), params->n_batch, &n_past, false);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
eval_string(ctx_llava->ctx_llama, std::string("</slice>").c_str(), params->n_batch, &n_past, false);
|
||||
}
|
||||
LOG_INF("%s: image token past: %d\n", __func__, n_past);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -597,7 +597,6 @@ elif args.minicpmv_projector is not None:
|
|||
fname_middle = "mmproj-"
|
||||
has_text_encoder = False
|
||||
has_minicpmv_projector = True
|
||||
minicpmv_version = 4
|
||||
elif args.vision_only:
|
||||
fname_middle = "vision-"
|
||||
has_text_encoder = False
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue