Merge pull request #10452 from ollama/drifkin/4096-context-length

config: update default context length to 4096

docs/faq.md

@@ -20,7 +20,7 @@ Please refer to the [GPU docs](./gpu.md).
 
 ## How can I specify the context window size?
 
-By default, Ollama uses a context window size of 2048 tokens. 
+By default, Ollama uses a context window size of 4096 tokens. 
 
 This can be overridden with the `OLLAMA_CONTEXT_LENGTH` environment variable. For example, to set the default context window to 8K, use: 
 

envconfig/config.go

@@ -169,7 +169,7 @@ var (
 	// Enable the new Ollama engine
 	NewEngine = Bool("OLLAMA_NEW_ENGINE")
 	// ContextLength sets the default context length
-	ContextLength = Uint("OLLAMA_CONTEXT_LENGTH", 2048)
+	ContextLength = Uint("OLLAMA_CONTEXT_LENGTH", 4096)
 )
 
 func String(s string) func() string {
@@ -255,7 +255,7 @@ func AsMap() map[string]EnvVar {
 		"OLLAMA_ORIGINS":           {"OLLAMA_ORIGINS", AllowedOrigins(), "A comma separated list of allowed origins"},
 		"OLLAMA_SCHED_SPREAD":      {"OLLAMA_SCHED_SPREAD", SchedSpread(), "Always schedule model across all GPUs"},
 		"OLLAMA_MULTIUSER_CACHE":   {"OLLAMA_MULTIUSER_CACHE", MultiUserCache(), "Optimize prompt caching for multi-user scenarios"},
-		"OLLAMA_CONTEXT_LENGTH":    {"OLLAMA_CONTEXT_LENGTH", ContextLength(), "Context length to use unless otherwise specified (default: 2048)"},
+		"OLLAMA_CONTEXT_LENGTH":    {"OLLAMA_CONTEXT_LENGTH", ContextLength(), "Context length to use unless otherwise specified (default: 4096)"},
 		"OLLAMA_NEW_ENGINE":        {"OLLAMA_NEW_ENGINE", NewEngine(), "Enable the new Ollama engine"},
 
 		// Informational

envconfig/config_test.go

@@ -279,8 +279,8 @@ func TestVar(t *testing.T) {
 
 func TestContextLength(t *testing.T) {
 	cases := map[string]uint{
-		"":     2048,
-		"4096": 4096,
+		"":     4096,
+		"2048": 2048,
 	}
 
 	for k, v := range cases {