config.json

{
    "_name_or_path": "/workspace/process/lumiopen_poro-34b/source",
    "apply_residual_connection_post_layernorm": false,
    "architectures": [
        "BloomForCausalLM"
    ],
    "attention_dropout": 0.0,
    "attention_softmax_in_fp32": true,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_dropout": 0.0,
    "hidden_size": 7168,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "masked_softmax_fusion": true,
    "model_type": "bloom",
    "n_head": 56,
    "n_layer": 54,
    "pad_token_id": 3,
    "pretraining_tp": 1,
    "slow_but_exact": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.35.2",
    "use_cache": true,
    "vocab_size": 128000,
    "quantization_config": {
        "bits": 4,
        "group_size": 32,
        "damp_percent": 0.1,
        "desc_act": true,
        "sym": true,
        "true_sequential": true,
        "model_name_or_path": null,
        "model_file_base_name": "model",
        "quant_method": "gptq"
    }
}