1c641e6aac
* `main`/`server`: rename to `llama` / `llama-server` for consistency w/ homebrew
* server: update refs -> llama-server
gitignore llama-server
* server: simplify nix package
* main: update refs -> llama
fix examples/main ref
* main/server: fix targets
* update more names
* Update build.yml
* rm accidentally checked in bins
* update straggling refs
* Update .gitignore
* Update server-llm.sh
* main: target name -> llama-cli
* Prefix all example bins w/ llama-
* fix main refs
* rename {main->llama}-cmake-pkg binary
* prefix more cmake targets w/ llama-
* add/fix gbnf-validator subfolder to cmake
* sort cmake example subdirs
* rm bin files
* fix llama-lookup-* Makefile rules
* gitignore /llama-*
* rename Dockerfiles
* rename llama|main -> llama-cli; consistent RPM bin prefixes
* fix some missing -cli suffixes
* rename dockerfile w/ llama-cli
* rename(make): llama-baby-llama
* update dockerfile refs
* more llama-cli(.exe)
* fix test-eval-callback
* rename: llama-cli-cmake-pkg(.exe)
* address gbnf-validator unused fread warning (switched to C++ / ifstream)
* add two missing llama- prefixes
* Updating docs for eval-callback binary to use new `llama-` prefix.
* Updating a few lingering doc references for rename of main to llama-cli
* Updating `run-with-preset.py` to use new binary names.
Updating docs around `perplexity` binary rename.
* Updating documentation references for lookup-merge and export-lora
* Updating two small `main` references missed earlier in the finetune docs.
* Update apps.nix
* update grammar/README.md w/ new llama-* names
* update llama-rpc-server bin name + doc
* Revert "update llama-rpc-server bin name + doc"
This reverts commit e474ef1df4.
* add hot topic notice to README.md
* Update README.md
* Update README.md
* rename gguf-split & quantize bins refs in **/tests.sh
---------
Co-authored-by: HanClinto <hanclinto@gmail.com>
53 lines
2.5 KiB
Bash
Executable file
53 lines
2.5 KiB
Bash
Executable file
#!/bin/bash
|
|
|
|
model_dir="/Users/cxt/model/llm/mobileVLM/MobileVLM-1.7B_processed"
|
|
projector_name="mmproj-model-f16.gguf"
|
|
llama_name="ggml-model-q4_k.gguf"
|
|
img_dir="/Users/cxt/model/llm"
|
|
img_name="demo.jpg"
|
|
prompt="A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\nWho is the author of this book? \nAnswer the question using a single word or phrase. ASSISTANT:"
|
|
# img_name="cat.jpeg"
|
|
# prompt="A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\nWhat is in the image? ASSISTANT:"
|
|
|
|
program_dir="build_64/bin"
|
|
binName="llama-llava-cli"
|
|
n_threads=4
|
|
|
|
|
|
deviceDir="/data/local/tmp"
|
|
saveDir="output"
|
|
if [ ! -d ${saveDir} ]; then
|
|
mkdir ${saveDir}
|
|
fi
|
|
|
|
|
|
function android_run() {
|
|
# # copy resource into device
|
|
# adb push ${model_dir}/${projector_name} ${deviceDir}/${projector_name}
|
|
# adb push ${model_dir}/${llama_name} ${deviceDir}/${llama_name}
|
|
adb push ${img_dir}/${img_name} ${deviceDir}/${img_name}
|
|
# copy program into device
|
|
adb push ${program_dir}/${binName} ${deviceDir}/${binName}
|
|
adb shell "chmod 0777 ${deviceDir}/${binName}"
|
|
|
|
# run
|
|
adb shell "echo cd ${deviceDir} ${deviceDir}/${binName} \
|
|
-m ${deviceDir}/${llama_name} \
|
|
--mmproj ${deviceDir}/${projector_name} \
|
|
-t ${n_threads} \
|
|
--image ${deviceDir}/${img_name} \
|
|
-p \"${prompt}\" \
|
|
> ${deviceDir}/${modelName}_${projector_name}_${n_threads}_${img_name}.txt"
|
|
adb shell "cd ${deviceDir}; pwd; ${deviceDir}/${binName} \
|
|
-m ${deviceDir}/${llama_name} \
|
|
--mmproj ${deviceDir}/${projector_name} \
|
|
-t ${n_threads} \
|
|
--image ${deviceDir}/${img_name} \
|
|
-p \"${prompt}\" \
|
|
>> ${deviceDir}/${modelName}_${projector_name}_${n_threads}_${img_name}.txt 2>&1"
|
|
adb pull ${deviceDir}/${modelName}_${projector_name}_${n_threads}_${img_name}.txt ${saveDir}
|
|
}
|
|
|
|
android_run
|
|
|
|
echo "android_run is Done!"
|