Drop old falcon backend (deprecated) (#1675)

Drop old falcon backend

backend/go/llm/falcon-ggml/main.go

@@ -1,23 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-
-import (
-	"flag"
-
-	transformers "github.com/go-skynet/LocalAI/backend/go/llm/transformers"
-
-	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &transformers.Falcon{}); err != nil {
-		panic(err)
-	}
-}

backend/go/llm/transformers/falcon.go

@@ -1,43 +0,0 @@
-package transformers
-
-// This is a wrapper to statisfy the GRPC service interface
-// It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
-import (
-	"fmt"
-
-	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-
-	transformers "github.com/go-skynet/go-ggml-transformers.cpp"
-)
-
-type Falcon struct {
-	base.SingleThread
-
-	falcon *transformers.Falcon
-}
-
-func (llm *Falcon) Load(opts *pb.ModelOptions) error {
-	model, err := transformers.NewFalcon(opts.ModelFile)
-	llm.falcon = model
-	return err
-}
-
-func (llm *Falcon) Predict(opts *pb.PredictOptions) (string, error) {
-	return llm.falcon.Predict(opts.Prompt, buildPredictOptions(opts)...)
-}
-
-// fallback to Predict
-func (llm *Falcon) PredictStream(opts *pb.PredictOptions, results chan string) error {
-	go func() {
-		res, err := llm.falcon.Predict(opts.Prompt, buildPredictOptions(opts)...)
-
-		if err != nil {
-			fmt.Println("err: ", err)
-		}
-		results <- res
-		close(results)
-	}()
-
-	return nil
-}