From cc17b02b23eb65b01e8bb82e20dc407edeff0a4b Mon Sep 17 00:00:00 2001
From: Josh Yan <jyan00017@gmail.com>
Date: Wed, 28 Aug 2024 09:58:23 -0700
Subject: [PATCH] update

---
 .gitattributes   | 1 +
 llm/llm.go       | 1 +
 server/images.go | 2 +-
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/.gitattributes b/.gitattributes
index f1c8bcb4..af2a9cc5 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,3 +1,4 @@
 llm/ext_server/* linguist-vendored
+llm/*.h linguist-vendored
 * text=auto
 *.go text eol=lf
diff --git a/llm/llm.go b/llm/llm.go
index 9a05ebea..4e2926e5 100644
--- a/llm/llm.go
+++ b/llm/llm.go
@@ -20,6 +20,7 @@ package llm
 import "C"
 
 import (
+	"errors"
 	"fmt"
 	"sync/atomic"
 	"time"
diff --git a/server/images.go b/server/images.go
index eff2a311..6266a788 100644
--- a/server/images.go
+++ b/server/images.go
@@ -435,7 +435,7 @@ func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantizatio
 						return err
 					}
 
-					tensorCount := len(baseLayer.GGML.Tensors())
+					tensorCount := len(baseLayer.GGML.Tensors().Items)
 					ft := baseLayer.GGML.KV().FileType()
 					if !slices.Contains([]string{"F16", "F32"}, ft.String()) {
 						return errors.New("quantization is only supported for F16 and F32 models")