preprocessor.json

{
    "module": "keras_hub.src.models.qwen3.qwen3_causal_lm_preprocessor",
    "class_name": "Qwen3CausalLMPreprocessor",
    "config": {
        "name": "qwen3_causal_lm_preprocessor_2",
        "trainable": true,
        "dtype": {
            "module": "keras",
            "class_name": "DTypePolicy",
            "config": {
                "name": "float32"
            },
            "registered_name": null
        },
        "tokenizer": {
            "module": "keras_hub.src.models.qwen3.qwen3_tokenizer",
            "class_name": "Qwen3Tokenizer",
            "config": {
                "name": "qwen3_tokenizer",
                "trainable": true,
                "dtype": {
                    "module": "keras",
                    "class_name": "DTypePolicy",
                    "config": {
                        "name": "int32"
                    },
                    "registered_name": null
                },
                "config_file": "tokenizer.json",
                "sequence_length": null,
                "add_prefix_space": false,
                "unsplittable_tokens": [
                    "<|quad_start|>",
                    "<|video_pad|>",
                    "<|fim_middle|>",
                    "<|repo_name|>",
                    "<tool_response>",
                    "<|vision_start|>",
                    "<tool_call>",
                    "<|im_end|>",
                    "<|object_ref_end|>",
                    "<|file_sep|>",
                    "</tool_call>",
                    "<|im_start|>",
                    "<|vision_end|>",
                    "<|box_end|>",
                    "<|vision_pad|>",
                    "<think>",
                    "</tool_response>",
                    "</think>",
                    "<|image_pad|>",
                    "<|quad_end|>",
                    "<|endoftext|>",
                    "<|fim_prefix|>",
                    "<|box_start|>",
                    "<|fim_suffix|>",
                    "<|object_ref_start|>",
                    "<|fim_pad|>"
                ]
            },
            "registered_name": "keras_hub>Qwen3Tokenizer"
        },
        "config_file": "preprocessor.json",
        "sequence_length": 1024,
        "add_start_token": true,
        "add_end_token": true
    },
    "registered_name": "keras_hub>Qwen3CausalLMPreprocessor"
}