update script approach to use covert.py --get-outfile flag

TinyLLama-v0-5M-F16.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546060a9fd2c8fed83f786439fa9b117df81a27450cafa5ff0c137f64e9dbdb6
-size 11082304
+oid sha256:f4dccfdb2707a0747e58dec0e1e21d48ccefafd0e9d74cafbc45803a615074c2
+size 10008160

TinyLLama-v0-5M-F16.llamafile

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209dc48cf6bdb3d9959a82db7d610be4c210b8569bb4ccace0a1df26aae6ca05
-size 17633572
+oid sha256:a6fee85a6906722ef26d7f8925485654220ac3870d56ec1b8e260919e2dc33a4
+size 19468831

llama.cpp

@@ -1 +1 @@
-Subproject commit 2cde18440c2ea76e9a281360061dc381e6a5902c
+Subproject commit 74fe2ea7a8d713da7378812215213ba74050cda6

llamafile

@@ -1 +1 @@
-Subproject commit cb92b32a6dfae4dff06d7333afe51f2b7224f709
+Subproject commit 790029485fdd3a81284efdcae1c0483a4d39a6a6

llamafile-creation.sh

@@ -1,5 +1,8 @@
 #!/bin/bash
 
+MODEL_DIR="maykeye_tinyllama"
+METADATA_FILE="maykeye_tinyllama-metadata.json"
+
 ###############################################################################
 # Pull both model folder, llamafile (for the engine) and llama.cpp (for the conversion script)
 echo == Prep Enviroment ==
@@ -21,27 +24,29 @@ make
 # ./o/llama.cpp/llava/llava-quantize --> /usr/local/bin/llava-quantize
 popd
 
+###############################################################################
+echo == What is our llamafile name going to be? ==
+OUTFILE=$(./llama.cpp/convert.py ${MODEL_DIR} --metadata ${METADATA_FILE} --outtype f16 --get-outfile)
+echo We will be aiming to generate $OUTFILE.llamafile
+
 ###############################################################################
 echo == Convert from safetensor to gguf ==
-./llama.cpp/convert.py maykeye_tinyllama --outtype f16 --metadata maykeye_tinyllama-metadata.json
-mv maykeye_tinyllama/TinyLLama-v0-5M-F16.gguf TinyLLama-v0-5M-F16.gguf
+./llama.cpp/convert.py ${MODEL_DIR} --metadata ${METADATA_FILE} --outtype f16
+mv ${MODEL_DIR}/${OUTFILE}.gguf ${OUTFILE}.gguf
 
 ###############################################################################
 echo == Generating Llamafile ==
-cp ./llamafile/o/llama.cpp/main/main TinyLLama-v0-5M-F16.llamafile
+cp ./llamafile/o/llama.cpp/main/main ${OUTFILE}.llamafile
 
 # Create an .args file with settings defaults
 cat >.args <<EOF
 -m
-TinyLLama-v0-5M-F16.gguf
+${OUTFILE}.gguf
 EOF
 
 # zip align engine, gguf and default args
-./llamafile/o/llamafile/zipalign -j0 \
-  TinyLLama-v0-5M-F16.llamafile \
-  TinyLLama-v0-5M-F16.gguf \
-  .args
+./llamafile/o/llamafile/zipalign -j0 ${OUTFILE}.llamafile ${OUTFILE}.gguf .args
 
 ###############################################################################
 echo == Test Output ==
-./TinyLLama-v0-5M-F16.llamafile --cli -p "hello world the gruff man said"
+./${OUTFILE}.llamafile --cli -p "hello world the gruff man said"