Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

llava : fix the script error in MobileVLM README (#9054)

Browse Source 
Signed-off-by: Erhu Feng <2748250768@qq.com>
This commit is contained in:
fengerhu1 2024-09-12 19:34:22 +08:00 committed by GitHub
parent d4c3c10fad
commit e665744317
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
examples/llava/MobileVLM-README.md
View File

@ -39,7 +39,7 @@ python ./examples/llava/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: 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 ```sh
python ./examples/llava/convert_image_encoder_to_gguf \ python ./examples/llava/convert_image_encoder_to_gguf.py \
-m path/to/clip-vit-large-patch14-336 \ -m path/to/clip-vit-large-patch14-336 \
--llava-projector path/to/MobileVLM-1.7B/llava.projector \ --llava-projector path/to/MobileVLM-1.7B/llava.projector \
--output-dir path/to/MobileVLM-1.7B \ --output-dir path/to/MobileVLM-1.7B \
@ -47,7 +47,7 @@ python ./examples/llava/convert_image_encoder_to_gguf \
``` ```
```sh ```sh
python ./examples/llava/convert_image_encoder_to_gguf \ python ./examples/llava/convert_image_encoder_to_gguf.py \
-m path/to/clip-vit-large-patch14-336 \ -m path/to/clip-vit-large-patch14-336 \
--llava-projector path/to/MobileVLM-1.7B_V2/llava.projector \ --llava-projector path/to/MobileVLM-1.7B_V2/llava.projector \
--output-dir path/to/MobileVLM-1.7B_V2 \ --output-dir path/to/MobileVLM-1.7B_V2 \
@ -57,12 +57,12 @@ python ./examples/llava/convert_image_encoder_to_gguf \
4. Use `examples/convert_legacy_llama.py` to convert the LLaMA part of LLaVA to GGUF: 4. Use `examples/convert_legacy_llama.py` to convert the LLaMA part of LLaVA to GGUF:
```sh ```sh
python ./examples/convert_legacy_llama.py path/to/MobileVLM-1.7B python ./examples/convert_legacy_llama.py path/to/MobileVLM-1.7B --skip-unknown
``` ```
5. Use `quantize` to convert LLaMA part's DataType from `fp16` to `q4_k` 5. Use `quantize` to convert LLaMA part's DataType from `fp32` to `q4_k`
```sh ```sh
./llama-quantize path/to/MobileVLM-1.7B/ggml-model-f16.gguf path/to/MobileVLM-1.7B/ggml-model-q4_k.gguf q4_k_s ./llama-quantize path/to/MobileVLM-1.7B/ggml-model-F32.gguf path/to/MobileVLM-1.7B/ggml-model-q4_k.gguf q4_k_s
``` ```
Now both the LLaMA part and the image encoder is in the `MobileVLM-1.7B` directory. Now both the LLaMA part and the image encoder is in the `MobileVLM-1.7B` directory.