config.json

{
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": null,
    "dtype": "bfloat16",
    "eos_token_id": 65492,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 576,
    "initializer_range": 0.02,
    "intermediate_size": 1536,
    "max_position_embeddings": 4096,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 9,
    "num_hidden_layers": 80,
    "num_key_value_heads": 3,
    "pad_token_id": 3,
    "pretraining_tp": 1,
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000,
    "tie_word_embeddings": true,
    "transformers_version": "4.57.1",
    "use_cache": true,
    "vocab_size": 65536
}