config.json

{
    "_name_or_path": "pygmalion-7b",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "badwordsids": [
        [
            0
        ]
    ],
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "max_position_embeddings": 2048,
    "max_sequence_length": 2048,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-06,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.28.1",
    "use_cache": true,
    "vocab_size": 32000,
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.1.8",
        "bits": 5.0,
        "head_bits": 6,
        "calibration": {
            "rows": 100,
            "length": 2048,
            "dataset": "wiki2.parquet"
        }
    }
}