From 7768d4de546bbde0f4894bc2ee12dbe15f730e25 Mon Sep 17 00:00:00 2001
From: Daniel J Walsh <dwalsh@redhat.com>
Date: Fri, 12 Apr 2024 09:12:16 -0400
Subject: [PATCH] Improve model_server Makefile.

Also improve description of models Containerfile.

Signed-off-by: Daniel J Walsh <dwalsh@redhat.com>
---
 models/Containerfile | 14 ++++++++++----
 models/Makefile      |  4 ++--
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/models/Containerfile b/models/Containerfile
index fefecb5b..a49d39c0 100644
--- a/models/Containerfile
+++ b/models/Containerfile
@@ -1,9 +1,15 @@
-#https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_S.gguf
-#https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf
-#https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q4_K_M.gguf
-#https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin
+# Suggested alternative open AI Models
+# 	    https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_S.gguf
+#	    https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf (Default)
+#	    https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q4_K_M.gguf
+#	    https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin
 # podman build --build-arg MODEL_URL=https://... -t quay.io/yourimage .
+#
 FROM registry.access.redhat.com/ubi9/ubi-micro:9.3-13
+
+# Can be substituted using the --build-arg defined above
 ARG MODEL_URL=https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf
+
+# By default the Model Server container image uses the AI Model stored in the model/model.file file.
 WORKDIR /model
 ADD $MODEL_URL /model/model.file
diff --git a/models/Makefile b/models/Makefile
index 0953b54a..d3f46a72 100644
--- a/models/Makefile
+++ b/models/Makefile
@@ -1,6 +1,6 @@
-MODEL ?= MODEL=https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf
+MODEL ?= https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf
 IMAGE ?= quay.io/ai-lab/llama:latest
 
 .PHONY: build
 build:
-	podman build --build-arg ${MODEL} -f Containerfile -t ${IMAGE} .
+	podman build $${MODEL:+--build-arg MODEL=$${MODEL}}  -f Containerfile -t ${IMAGE} .