config.json

{
    "architectures": [
        "LlamaForCausalLM"
    ],
    "bos_token_id": 0,
    "eos_token_id": 1,
    "hidden_act": "silu",
    "hidden_size": 6656,
    "initializer_range": 0.02,
    "intermediate_size": 17920,
    "max_position_embeddings": 2048,
    "max_sequence_length": 2048,
    "model_type": "llama",
    "num_attention_heads": 52,
    "num_hidden_layers": 60,
    "pad_token_id": -1,
    "quantization": {
        "group_size": 64,
        "bits": 8
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8
    },
    "rms_norm_eps": 1e-06,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.31.0.dev0",
    "use_cache": true,
    "vocab_size": 32000
}