feat(llama2): add template for chat messages (#782)

Co-authored-by: Aman Karmani <aman@tmm1.net>

Lays some of the groundwork for LLAMA2 compatibility as well as other future models with complex prompting schemes.

Started small refactoring in pkg/model/loader.go regarding template loading. Currently still a part of ModelLoader, but should be easy to add template loading for situations other than overall prompt templates and the new chat-specific per-message templates
Adds support for new chat-endpoint-specific, per-message templates as an alternative to the existing Role: XYZ sprintf method.
Includes a temporary prompt template as an example, since I have a few questions before we merge in the model-gallery side changes (see )
Minor debug logging changes.

tests/integration/reflect_test.go

@@ -0,0 +1,23 @@
+package integration_test
+
+import (
+	"reflect"
+
+	config "github.com/go-skynet/LocalAI/api/config"
+	model "github.com/go-skynet/LocalAI/pkg/model"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = Describe("Integration Tests involving reflection in liue of code generation", func() {
+	Context("config.TemplateConfig and model.TemplateType must stay in sync", func() {
+
+		ttc := reflect.TypeOf(config.TemplateConfig{})
+
+		It("TemplateConfig and TemplateType should have the same number of valid values", func() {
+			const lastValidTemplateType = model.IntegrationTestTemplate - 1
+			Expect(lastValidTemplateType).To(Equal(ttc.NumField()))
+		})
+
+	})
+})