EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

mtmd : rename llava directory to mtmd (#13311)

Browse Source 
* mv llava to mtmd

* change ref everywhere
This commit is contained in:
Xuan-Son Nguyen
2025-05-05 16:02:55 +02:00
committed by GitHub
parent 5215b91e93
commit 9b61acf060
37 changed files with 44 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/multimodal/MobileVLM.md
View File

@@ -33,13 +33,13 @@ git clone https://huggingface.co/openai/clip-vit-large-patch14-336
2. Use `llava_surgery.py` to split the LLaVA model to LLaMA and multimodel projector constituents:
```sh
python ./tools/llava/llava_surgery.py -m path/to/MobileVLM-1.7B
python ./tools/mtmd/llava_surgery.py -m path/to/MobileVLM-1.7B
```
3. Use `convert_image_encoder_to_gguf.py` with `--projector-type ldp` (for **V2** please use `--projector-type ldpv2`) to convert the LLaVA image encoder to GGUF:
```sh
python ./tools/llava/convert_image_encoder_to_gguf.py \
python ./tools/mtmd/convert_image_encoder_to_gguf.py \
-m path/to/clip-vit-large-patch14-336 \
--llava-projector path/to/MobileVLM-1.7B/llava.projector \
--output-dir path/to/MobileVLM-1.7B \
@@ -47,7 +47,7 @@ python ./tools/llava/convert_image_encoder_to_gguf.py \
```
```sh
python ./tools/llava/convert_image_encoder_to_gguf.py \
python ./tools/mtmd/convert_image_encoder_to_gguf.py \
-m path/to/clip-vit-large-patch14-336 \
--llava-projector path/to/MobileVLM-1.7B_V2/llava.projector \
--output-dir path/to/MobileVLM-1.7B_V2 \
@@ -69,10 +69,10 @@ Now both the LLaMA part and the image encoder is in the `MobileVLM-1.7B` directo
## Android compile and run
### compile
refer to `tools/llava/android/build_64.sh`
refer to `tools/mtmd/android/build_64.sh`
```sh
mkdir tools/llava/android/build_64
cd tools/llava/android/build_64
mkdir tools/mtmd/android/build_64
cd tools/mtmd/android/build_64
../build_64.sh
```
### run on Android