Removed 8-bit quantization and changed model_id to google/gemma-3n-E4B-it-litert-preview cb3e313 Jeff Myers II commited on Jun 17
Enabling 8-bit quantization broke the model. Attempting to fix by removing 'pad_token_id' arg from AutoModelForCausalLM.from_pretrained 5278642 Jeff Myers II commited on Jun 17