Do not take all CPU by default (#50)

main.go

@@ -2,13 +2,12 @@ package main
 
 import (
 	"os"
-	"runtime"
 
 	api "github.com/go-skynet/LocalAI/api"
 	model "github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/jaypipes/ghw"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
-
 	"github.com/urfave/cli/v2"
 )
 
@@ -21,6 +20,12 @@ func main() {
 		os.Exit(1)
 	}
 
+	threads := 4
+	cpu, err := ghw.CPU()
+	if err == nil {
+		threads = int(cpu.TotalCores)
+	}
+
 	app := &cli.App{
 		Name:  "LocalAI",
 		Usage: "OpenAI compatible API for running LLaMA/GPT models locally on CPU with consumer grade hardware.",
@@ -37,7 +42,7 @@ func main() {
 				Name:        "threads",
 				DefaultText: "Number of threads used for parallel computation. Usage of the number of physical cores in the system is suggested.",
 				EnvVars:     []string{"THREADS"},
-				Value:       runtime.NumCPU(),
+				Value:       threads,
 			},
 			&cli.StringFlag{
 				Name:        "models-path",