Error when pressing the "generate" button

[~Komod~]

Godot Engine v3.5.1.stable.custom_build.6fed1ffa3 - https://godotengine.org
OpenGL ES 3.0 Renderer: GeForce GT 750M/PCIe/SSE2
Async. shader compilation: OFF

AIdventure (Godot 3.5.1 stable)
Type help to get more information about usage
2024/02/21 18:29:10
Game version: 1.5.3.STEAM
OS: Windows
Press F1 to close the console.
Initialized Steam. Steamworks active.
remote_server : false
ERROR: Connection lost with the server. clean: False
at: GDScriptFunctions::call (modules\gdscript\gdscript_functions.cpp:775) - Connection lost with the server. clean: False

===== Server's logs dump =====
18:29:41,458 AIdventure_Server INFO Server started ws://0.0.0.0:9999
18:29:45,165 AIdventure_Server INFO Client 127.0.0.1 connected
18:29:48,872 AIdventure_Server INFO Setting up the model.
18:29:49,404 AIdventure_Server INFO Tokens successfully loaded from local files
18:31:21,472 AIdventure_Server INFO Model successfully loaded from local files
18:31:21,499 AIdventure_Server INFO Is CUDA available: False
18:31:50,755 AIdventure_Server ERROR "LayerNormKernelImpl" not implemented for 'Half'
18:31:50,756 AIdventure_Server INFO Shutting down the server
18:31:51,413 asyncio ERROR Task exception was never retrieved
future: <Task finished name='Task-5' coro=<WebSocketServerProtocol.handler() done, defined at D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\websockets\legacy\server.py:153> exception=SystemExit(0)>
Traceback (most recent call last):
File "D:\SteAm\steamapps\common\AIdventure\server\server.py", line 137, in handler
data_to_send = handle_request(p_websocket, json_message)
File "D:\SteAm\steamapps\common\AIdventure\server\server.py", line 169, in handle_request
generated_text = generator.generate_text(prompt,
File "D:\SteAm\steamapps\common\AIdventure\server\generator.py", line 60, in generate_text
model_output = self._Model.generate(**model_input)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\transformers\generation\utils.py", line 1452, in generate
return self.sample(
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\transformers\generation\utils.py", line 2468, in sample
outputs = self(
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\accelerate\hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\transformers\models\gpt2\modeling_gpt2.py", line 1075, in forward
transformer_outputs = self.transformer(
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\transformers\models\gpt2\modeling_gpt2.py", line 899, in forward
outputs = block(
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\accelerate\hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\transformers\models\gpt2\modeling_gpt2.py", line 388, in forward
hidden_states = self.ln_1(hidden_states)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\accelerate\hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\torch\nn\modules\normalization.py", line 190, in forward
return F.layer_norm(
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\torch\nn\functional.py", line 2515, in layer_norm
return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\SteAm\steamapps\common\AIdventure\server\server.py", line 268, in <module>
asyncio.run(main())
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\asyncio\runners.py", line 44, in run
return loop.run_until_complete(main)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\asyncio\base_events.py", line 629, in run_until_complete
self.run_forever()
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\asyncio\windows_events.py", line 316, in run_forever
super().run_forever()
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\asyncio\base_events.py", line 596, in run_forever
self._run_once()
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\asyncio\base_events.py", line 1890, in _run_once
handle._run()
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\asyncio\events.py", line 80, in _run
self._context.run(self._callback, *self._args)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\websockets\legacy\server.py", line 236, in handler
await self.ws_handler(self)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\site-packages\websockets\legacy\server.py", line 1175, in _ws_handler
return await cast(
File "D:\SteAm\steamapps\common\AIdventure\server\server.py", line 150, in handler
shutdown_server(exit_code)
File "D:\SteAm\steamapps\common\AIdventure\server\server.py", line 254, in shutdown_server
exit(p_exit_code)
File "D:\SteAm\steamapps\common\AIdventure\mamba\envs\aidventure\lib\_sitebuiltins.py", line 26, in __call__
raise SystemExit(code)
SystemExit: 0

[Lyaaaaaaaaaaaaaaa]

Hello, the problem is because of the torch_dtype option (you can find it in the ai_settings, in advanced options) is set to float16 instead of float32. This is the issue when CUDA is not available.
"18:31:21,499 AIdventure_Server INFO Is CUDA available: False"

However, I checked on https://developer.nvidia.com/cuda-gpus#collapse2 and it says your GPU supports CUDA. So I recommend you to verify if your Nvidia's drivers are up to date!