config.json

{
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "bos_token_id": 2,
    "eos_token_id": 3,
    "hidden_act": "silu",
    "hidden_size": 1280,
    "intermediate_size": 3456,
    "max_position_embeddings": 32768,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 20,
    "num_hidden_layers": 24,
    "num_key_value_heads": 20,
    "pad_token_id": 1,
    "quantization": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
        "rope_type": "yarn",
        "factor": 4.0,
        "original_max_position_embeddings": 8192
    },
    "rope_theta": 10000.0,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "vocab_size": 32000
}