model-conversion : add embedding prompt file support (#15871)

This commit adds support for passing a prompt file to the model
conversion targets/scripts. It also updates the logits.cpp to print out
embedding information in the same format as when running the original
embedding model.

The motivation for this is that it allows us to pass files of different
sizes when running the converted models and validating the logits.

This can be particularly important when testing the sliding window
functionality of models where the sequence length needs to exceed a
certain number of tokens to trigger the sliding window logic.

examples/model-conversion/scripts/embedding/run-converted-model.sh

@@ -2,8 +2,27 @@
 
 set -e
 
-# First try command line argument, then environment variable, then file
-CONVERTED_MODEL="${1:-"$CONVERTED_EMBEDDING_MODEL"}"
+# Parse command line arguments
+CONVERTED_MODEL=""
+PROMPTS_FILE=""
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -p|--prompts-file)
+            PROMPTS_FILE="$2"
+            shift 2
+            ;;
+        *)
+            if [ -z "$CONVERTED_MODEL" ]; then
+                CONVERTED_MODEL="$1"
+            fi
+            shift
+            ;;
+    esac
+done
+
+# First try command line argument, then environment variable
+CONVERTED_MODEL="${CONVERTED_MODEL:-"$CONVERTED_EMBEDDING_MODEL"}"
 
 # Final check if we have a model path
 if [ -z "$CONVERTED_MODEL" ]; then
@@ -13,8 +32,19 @@ if [ -z "$CONVERTED_MODEL" ]; then
     exit 1
 fi
 
+# Read prompt from file or use default
+if [ -n "$PROMPTS_FILE" ]; then
+    if [ ! -f "$PROMPTS_FILE" ]; then
+        echo "Error: Prompts file '$PROMPTS_FILE' not found" >&2
+        exit 1
+    fi
+    PROMPT=$(cat "$PROMPTS_FILE")
+else
+    PROMPT="Hello world today"
+fi
+
 echo $CONVERTED_MODEL
 
 cmake --build ../../build --target llama-logits -j8
-
-../../build/bin/llama-logits -m "$CONVERTED_MODEL" -embd-mode "Hello world today"
+# TODO: update logits.cpp to accept a --file/-f option for the prompt
+../../build/bin/llama-logits -m "$CONVERTED_MODEL" -embd-mode "$PROMPT"