python main. py 
    Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
model. safetensors.index.json: 100%|
| 13.5k/13.5k [00:00‹?, PB/s]
model-00001-of-00002. safetensors: 100%
| 4.95G/4.95G [07:27<00:00, 11. 1MB/s]
model-00002-of-00002. safetensors: 100%
67. 1M/67.1M [00:05<00:00, 11.5MB/s]
Downloading shards: 100% ||
| 2/2 [07:35‹00:00, 227.61s/it]
Gemma's activation function should be approximate GeLU and not exact GeLU. Changing the activation function to 'gelu_pytorch_tanh.if you want to use the legacy "gelu', edit the "model.config to
set hidden_activation=gelu*
instead of todden act
instead of hidden_act. See https://github.com/huggingface/transformers/pull/29402 for
more details.
Loading checkpoint shards: 100%|
| 2/2 [00:03<00:00, 1.87s/itl
generation_config json: 100%||
137/137［00:00<？」3B/s］
nexa model result:
a pouto using the specified caea and resolutiou stones iption: rame rs a photo (cama a):)
Captures
- camera (str): Specifies the camera
to use. Can be \'front\' or \'back\'. The default is \'back\'. \n\n
Returns: \n
- str: The string contains the file
2624 t 12 4a. 
Photo if nees at ay 96 83662387968t, ample: /storage/emulated/o/Pictures/NAPP/3N
123456.Jpg\'\n latency: 367.85967230796814