config.json

{
    "_name_or_path": "/abacus/training_runs/arka/acm_rewrite_llama-3-70b/merged-200/",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "hidden_act": "silu",
    "hidden_size": 8192,
    "initializer_range": 0.02,
    "intermediate_size": 28672,
    "max_position_embeddings": 8192,
    "model_type": "llama",
    "num_attention_heads": 64,
    "num_hidden_layers": 80,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.40.0",
    "use_cache": true,
    "use_flash_attention_2": true,
    "vocab_size": 128256,
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.0.21",
        "bits": 8.1,
        "head_bits": 8,
        "calibration": {
            "rows": 100,
            "length": 2048,
            "dataset": "(default)"
        }
    }
}