{
    "_name_or_path": "/workspace/process/llama-68m",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "bos_token_id": 0,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "max_position_embeddings": 2048,
    "model_type": "llama",
    "num_attention_heads": 12,
    "num_hidden_layers": 2,
    "num_key_value_heads": 12,
    "pad_token_id": 1,
    "pretraining_tp": 1,
    "quantization_config": {
        "batch_size": 1,
        "bits": 4,
        "block_name_to_quantize": "model.layers",
        "cache_block_outputs": true,
        "damp_percent": 0.1,
        "desc_act": true,
        "exllama_config": {
            "version": 1
        },
        "group_size": 128,
        "max_input_length": null,
        "model_seqlen": 4096,
        "module_name_preceding_first_block": [
            "model.embed_tokens"
        ],
        "pad_token_id": null,
        "quant_method": "gptq",
        "sym": true,
        "tokenizer": null,
        "true_sequential": true,
        "use_cuda_fp16": true,
        "use_exllama": false
    },
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.35.0",
    "use_cache": true,
    "vocab_size": 32000
}