llm_config.json

{
    "model_type": "gemma4",
    "hidden_size": 2560,
    "attention_mask": "float",
    "attention_type": "mix",
    "is_mrope": false,
    "layer_nums": 42,
    "hidden_size_per_layer_input": 256,
    "per_layer_embedding_hidden_size": 10752,
    "per_layer_embedding_file": "per_layer_embeddings_int4.bin",
    "per_layer_scale_emb": 16.0,
    "use_template": true,
    "force_full_decode_recompute": false,
    "jinja": {
        "chat_template": "{{ bos_token }}{% for message in messages %}{% if message.role == \"system\" %}<|turn>system\n{{ message.content }}<turn|>\n{% elif message.role == \"user\" %}<|turn>user\n{{ message.content }}<turn|>\n{% elif message.role == \"assistant\" %}<|turn>model\n{{ message.content }}<turn|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|turn>model\n{% endif %}",
        "bos": "<bos>",
        "eos": "<turn|>"
    },
    "scale_emb": 50.5,
    "sampler_type": "mixed",
    "temperature": 1.0,
    "top_k": 64,
    "top_p": 0.95,
    "min_p": 0.0,
    "tfs_z": 1.0,
    "typical": 1.0,
    "repetition_penalty": 1.0,
    "presence_penalty": 0.0,
    "frequency_penalty": 0.0,
    "penalty_window": 0,
    "n_gram": 8,
    "ngram_factor": 1.0,
    "sliding_window": 512,
    "tie_embeddings": [
        0,
        335544320,
        41943040,
        4,
        128
    ],
    "ple_quant": [
        0,
        1409286144,
        176160768,
        4,
        128
    ]
}