preprocessor.json

{
    "module": "keras_hub.src.models.llama3.llama3_causal_lm_preprocessor",
    "class_name": "Llama3CausalLMPreprocessor",
    "config": {
        "name": "llama3_causal_lm_preprocessor",
        "trainable": true,
        "dtype": {
            "module": "keras",
            "class_name": "DTypePolicy",
            "config": {
                "name": "float32"
            },
            "registered_name": null
        },
        "tokenizer": {
            "module": "keras_hub.src.models.llama3.llama3_tokenizer",
            "class_name": "Llama3Tokenizer",
            "config": {
                "name": "llama3_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": [
                    "<|eom_id|>",
                    "<|eot_id|>",
                    "<|finetune_right_pad_id|>",
                    "<|begin_of_text|>",
                    "<|python_tag|>",
                    "<|start_header_id|>",
                    "<|end_of_text|>",
                    "<|end_header_id|>"
                ]
            },
            "registered_name": "keras_hub>Llama3Tokenizer"
        },
        "config_file": "preprocessor.json",
        "sequence_length": 1024,
        "add_start_token": true,
        "add_end_token": true
    },
    "registered_name": "keras_hub>Llama3CausalLMPreprocessor"
}