Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

docs: add the no-Modelfile function of `ollama create` (#9077)

frob802ad16ce443
diff --git a/cmd/cmd.go b/cmd/cmd.go
index c661df4e7..7955012c8 100644
--- a/cmd/cmd.go
+++ b/cmd/cmd.go
@@ -1418,13 +1418,13 @@ func NewCLI() *cobra.Command {
createCmd := &cobra.Command{
Use: "create MODEL",
- Short: "Create a model from a Modelfile",
+ Short: "Create a model",
Args: cobra.ExactArgs(1),
PreRunE: checkServerHeartbeat,
RunE: CreateHandler,
}
- createCmd.Flags().StringP("file", "f", "", "Name of the Modelfile (default \"Modelfile\"")
+ createCmd.Flags().StringP("file", "f", "", "Name of the Modelfile (default \"Modelfile\")")
createCmd.Flags().StringP("quantize", "q", "", "Quantize model to this level (e.g. q4_K_M)")
showCmd := &cobra.Command{
diff --git a/docs/import.md b/docs/import.md
index df06ce4b3..104b4162c 100644
--- a/docs/import.md
+++ b/docs/import.md
@@ -53,6 +53,8 @@ FROM /path/to/safetensors/directory
If you create the Modelfile in the same directory as the weights, you can use the command `FROM .`.
+If you do not create the Modelfile, ollama will act as if there was a Modelfile with the command `FROM .`.
+
Now run the `ollama create` command from the directory where you created the `Modelfile`:
```shell