Force llama.cpp to output only one line - annna - Annna the nice friendly bot.
 (HTM) git clone git://bitreich.org/annna/ git://enlrupgkhuxnvlhsf6lc3fziv5h2hhfrinws65d7roiv6bfj7d652fid.onion/annna/
 (DIR) Log
 (DIR) Files
 (DIR) Refs
 (DIR) Tags
 (DIR) README
       ---
 (DIR) commit bef238f14dbe190805e443abd9026f6ede912668
 (DIR) parent 5e293f40c97b744439f3cabeb19ae749388b9116
 (HTM) Author: Julian Schweinsberg <pazz0@0xfa.de>
       Date:   Mon, 11 Nov 2024 13:02:58 +0100
       
       Force llama.cpp to output only one line
       
       sed is used to remove leading whitespace and the [end of text]-Thing
       which can occur if less then the maximal token count was outputted.
       
       head -n1 is used to remove the empty leading line which got outputted in
       my testing.
       
       Signed-off-by: Annna Robert-Houdin <annna@bitreich.org>
       
       Diffstat:
         M gpt                                 |      10 +++++-----
       
       1 file changed, 5 insertions(+), 5 deletions(-)
       ---
 (DIR) diff --git a/gpt b/gpt
       @@ -3,16 +3,16 @@
        #ggmlbase="/br/ai/ggml"
        ggmlbase="/br/ai/llama.cpp"
        #ggmlbin="./build/bin/gpt-2"
       -ggmlbin="./build/bin/llama-simple"
       +ggmlbin="./build/bin/llama-cli"
        #ggmlmodel="models/gpt-2-1558M/ggml-model.bin"
        ggmlmodel="models/zephyr-7b-beta.Q4_0.gguf"
        ggmlntokens="69"
        
        cd $ggmlbase
        $ggmlbin -m $ggmlmodel -n $ggmlntokens \
       -        "$1 Begin all lines with OUTPUT:." 2>/dev/null \
       -        | grep "^OUTPUT:" \
       -        | cut -d':' -f 2- \
       -        | head -n 1 \
       +        --simple-io --no-display-prompt --grammar 'root ::= ([^\x00-\x1F])*' \
       +        -p "$1" 2>/dev/null \
       +        | head -n1 \
       +        | sed -E 's/^[[:blank:]]+//;s/[[:blank:]]*\[end of text\]$//' \
                | tr -d '"'