Add 'device' to GPT4All (#11216)

Add device to GPT4All

- **Description:** GPT4All now supports GPU. This commit adds the option
to enable it.
- **Issue:** It closes
https://github.com/langchain-ai/langchain/issues/10486

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

libs/langchain/langchain/llms/gpt4all.py

@@ -89,6 +89,9 @@ class GPT4All(LLM):
     allow_download: bool = False
     """If model does not exist in ~/.cache/gpt4all/, download it."""
 
+    device: Optional[str] = Field("cpu", alias="device")
+    """Device name: cpu, gpu, nvidia, intel, amd or DeviceName."""
+
     client: Any = None  #: :meta private:
 
     class Config:
@@ -141,6 +144,7 @@ class GPT4All(LLM):
             model_path=model_path or None,
             model_type=values["backend"],
             allow_download=values["allow_download"],
+            device=values["device"],
         )
         if values["n_threads"] is not None:
             # set n_threads