config.json

{
    "activation_function": "gelu_pytorch_tanh",
    "architectures": [
        "GPTBigCodeForCausalLM"
    ],
    "attention_softmax_in_fp32": true,
    "attn_pdrop": 0.1,
    "bos_token_id": 0,
    "embd_pdrop": 0.1,
    "eos_token_id": 0,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "model_type": "gpt_bigcode",
    "multi_query": true,
    "n_embd": 6144,
    "n_head": 48,
    "n_inner": 24576,
    "n_layer": 52,
    "n_positions": 8192,
    "pad_token_id": 0,
    "resid_pdrop": 0.1,
    "scale_attention_softmax_in_fp32": true,
    "scale_attn_weights": true,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.41.0.dev0",
    "use_cache": true,
    "vocab_size": 49152,
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.0.21",
        "bits": 8.0,
        "head_bits": 8,
        "calibration": {
            "rows": 100,
            "length": 2048,
            "dataset": "(default)"
        }
    }
}