Merge branch 'ollama:main' into main

cmd/cmd.go

@@ -1050,7 +1050,7 @@ func NewCLI() *cobra.Command {
 		RunE:    CreateHandler,
 	}
 
-	createCmd.Flags().StringP("file", "f", "Modelfile", "Name of the Modelfile (default \"Modelfile\")")
+	createCmd.Flags().StringP("file", "f", "Modelfile", "Name of the Modelfile")
 	createCmd.Flags().StringP("quantize", "q", "", "Quantize model to this level (e.g. q4_0)")
 
 	showCmd := &cobra.Command{

openai/openai.go

@@ -107,9 +107,14 @@ func toChatCompletion(id string, r api.ChatResponse) ChatCompletion {
 		Model:             r.Model,
 		SystemFingerprint: "fp_ollama",
 		Choices: []Choice{{
-			Index:        0,
-			Message:      Message{Role: r.Message.Role, Content: r.Message.Content},
-			FinishReason: &r.DoneReason,
+			Index:   0,
+			Message: Message{Role: r.Message.Role, Content: r.Message.Content},
+			FinishReason: func(reason string) *string {
+				if len(reason) > 0 {
+					return &reason
+				}
+				return nil
+			}(r.DoneReason),
 		}},
 		Usage: Usage{
 			// TODO: ollama returns 0 for prompt eval if the prompt was cached, but openai returns the actual count
@@ -127,13 +132,16 @@ func toChunk(id string, r api.ChatResponse) ChatCompletionChunk {
 		Created:           time.Now().Unix(),
 		Model:             r.Model,
 		SystemFingerprint: "fp_ollama",
-		Choices: []ChunkChoice{
-			{
-				Index:        0,
-				Delta:        Message{Role: "assistant", Content: r.Message.Content},
-				FinishReason: &r.DoneReason,
-			},
-		},
+		Choices: []ChunkChoice{{
+			Index: 0,
+			Delta: Message{Role: "assistant", Content: r.Message.Content},
+			FinishReason: func(reason string) *string {
+				if len(reason) > 0 {
+					return &reason
+				}
+				return nil
+			}(r.DoneReason),
+		}},
 	}
 }
 

server/envconfig/config_test.go

@@ -1,20 +1,20 @@
 package envconfig
 
 import (
-	"os"
 	"testing"
 
 	"github.com/stretchr/testify/require"
 )
 
 func TestConfig(t *testing.T) {
-	os.Setenv("OLLAMA_DEBUG", "")
+	Debug = false // Reset whatever was loaded in init()
+	t.Setenv("OLLAMA_DEBUG", "")
 	LoadConfig()
 	require.False(t, Debug)
-	os.Setenv("OLLAMA_DEBUG", "false")
+	t.Setenv("OLLAMA_DEBUG", "false")
 	LoadConfig()
 	require.False(t, Debug)
-	os.Setenv("OLLAMA_DEBUG", "1")
+	t.Setenv("OLLAMA_DEBUG", "1")
 	LoadConfig()
 	require.True(t, Debug)
 }

types/model/name.go

@@ -291,11 +291,9 @@ func (n Name) Filepath() string {
 		panic("illegal attempt to get filepath of invalid name")
 	}
 	return filepath.Join(
-		strings.ToLower(filepath.Join(
-			n.Host,
-			n.Namespace,
-			n.Model,
-		)),
+		n.Host,
+		n.Namespace,
+		n.Model,
 		n.Tag,
 	)
 }

types/model/name_test.go

@@ -276,9 +276,9 @@ func TestFilepathAllocs(t *testing.T) {
 	allocs := testing.AllocsPerRun(1000, func() {
 		n.Filepath()
 	})
-	var allowedAllocs float64 = 3
+	var allowedAllocs float64 = 1
 	if runtime.GOOS == "windows" {
-		allowedAllocs = 5
+		allowedAllocs = 3
 	}
 	if allocs > allowedAllocs {
 		t.Errorf("allocs = %v; allowed %v", allocs, allowedAllocs)