{"record":{"id":"39180255360187ed","repo":"invoke-ai/InvokeAI","slug":"expected-pretrainedtokenizerbase-for-gemma-tokeniz-391802","errorCode":null,"errorMessage":"Expected PreTrainedTokenizerBase for Gemma tokenizer, got {type(gemma_tokenizer).__name__}.","messagePattern":"Expected PreTrainedTokenizerBase for Gemma tokenizer, got (.+?)\\.","errorType":"exception","errorClass":"TypeError","httpStatus":null,"severity":"error","filePath":"invokeai/app/invocations/z_image_pid_decode.py","lineNumber":142,"sourceCode":"                    shift_factor = float(getattr(vae, \"shift_factor\", shift_factor))\n            del vae_info\n            TorchDevice.empty_cache()\n        context.logger.info(\n            f\"Z-Image PiD decode: latent shape={tuple(latents.shape)} dtype={latents.dtype} \"\n            f\"stats[min={latents.min().item():.3f} max={latents.max().item():.3f} \"\n            f\"mean={latents.mean().item():.3f}] using scale={scaling_factor:.4f} shift={shift_factor:.4f}\"\n        )\n\n        # 2) Encode caption with Gemma-2.\n        gemma_text_encoder_info = context.models.load(self.gemma2_encoder.text_encoder)\n        gemma_tokenizer_info = context.models.load(self.gemma2_encoder.tokenizer)\n        with ExitStack() as stack:\n            (_, gemma_encoder) = stack.enter_context(gemma_text_encoder_info.model_on_device())\n            (_, gemma_tokenizer) = stack.enter_context(gemma_tokenizer_info.model_on_device())\n            if not isinstance(gemma_encoder, PreTrainedModel):\n                raise TypeError(f\"Expected PreTrainedModel for Gemma encoder, got {type(gemma_encoder).__name__}.\")\n            if not isinstance(gemma_tokenizer, PreTrainedTokenizerBase):\n                raise TypeError(\n                    f\"Expected PreTrainedTokenizerBase for Gemma tokenizer, got {type(gemma_tokenizer).__name__}.\"\n                )\n\n            # Encode on the encoder's intended compute device. compute_device honours cpu_only and is\n            # stable under partial loading — the first parameter may be offloaded to CPU while later\n            # modules load on CUDA, so inferring the device from the first parameter could place caption\n            # inputs on the wrong device.\n            device = gemma_text_encoder_info.compute_device\n            encode_dtype = TorchDevice.choose_bfloat16_safe_dtype(device)\n\n            context.util.signal_progress(\"Encoding caption with Gemma-2\")\n            caption_embs, caption_mask = encode_caption_for_pid(\n                [self.prompt],\n                tokenizer=gemma_tokenizer,\n                encoder=gemma_encoder,\n                device=device,\n                dtype=encode_dtype,\n            )","sourceCodeStart":124,"sourceCodeEnd":160,"githubUrl":"https://github.com/invoke-ai/InvokeAI/blob/0b6a024f2ff6a86bfb953dcdb9cc504ef7397a06/invokeai/app/invocations/z_image_pid_decode.py#L124-L160","documentation":"In the same invoke of z_image_pid_decode.py, the Gemma tokenizer loaded from the gemma2_encoder submodel must be a transformers PreTrainedTokenizerBase. If model_on_device returns anything else, a TypeError is raised with the actual type name. This ensures tokenization of captions uses a real HF tokenizer API.","triggerScenarios":"Invoking the PiD decode path where context.models.load(self.gemma2_encoder.tokenizer).model_on_device() yields an object failing isinstance(gemma_tokenizer, PreTrainedTokenizerBase).","commonSituations":"Tokenizer directory missing tokenizer.json/tokenizer_config.json so a fallback object is loaded; wrong submodel wired to the tokenizer field; incompatible transformers version or corrupted download.","solutions":["Re-download the Gemma tokenizer files (tokenizer.json, tokenizer_config.json, special_tokens_map.json).","Confirm the gemma2_encoder.tokenizer submodel reference points to a valid tokenizer model config.","Update transformers/InvokeAI so tokenizers load as PreTrainedTokenizerBase.","Re-import the Gemma encoder model through the model manager to rebuild tokenizer metadata."],"exampleFix":null,"handlingStrategy":"type-guard","validationCode":"with context.models.load(tokenizer_key).model_on_device() as (_, tok):\n    if not isinstance(tok, PreTrainedTokenizerBase):\n        fail_fast(tok)","typeGuard":"def is_hf_tokenizer(obj) -> bool:\n    from transformers import PreTrainedTokenizerBase\n    return isinstance(obj, PreTrainedTokenizerBase)","tryCatchPattern":"try:\n    decode(context)\nexcept TypeError as e:\n    if \"Expected PreTrainedTokenizerBase for Gemma tokenizer\" in str(e):\n        reinstall_tokenizer_files()\n    else:\n        raise","preventionTips":["Ensure tokenizer.json/tokenizer_config.json ship with the Gemma encoder download.","Never bind a non-tokenizer submodel into the tokenizer field.","Re-scan the models folder after manual edits to tokenizer files."],"tags":["type-check","tokenizer","gemma","z-image"],"backgroundTag":"unexpected-model-type","analyzedSha":"0b6a024f2ff6a86bfb953dcdb9cc504ef7397a06","analyzedAt":"2026-08-29T04:46:49.967Z","schemaVersion":2},"datasetVersion":"2026-08-29T07:17:48.351Z"}