{
    "_name_or_path": "/covalent/.cache/models/tmpln5zvbdg1k8ewf_i",
    "activation_function": "gelu_new",
    "all_reduce_scores": {
        "0": "NON_PARTICIPATING",
        "1": "NON_PARTICIPATING",
        "10": "NON_PARTICIPATING",
        "11": "NON_PARTICIPATING",
        "12": "NON_PARTICIPATING",
        "13": "NON_PARTICIPATING",
        "14": "NON_PARTICIPATING",
        "15": "NON_PARTICIPATING",
        "16": "NON_PARTICIPATING",
        "17": "NON_PARTICIPATING",
        "18": "NON_PARTICIPATING",
        "19": "NON_PARTICIPATING",
        "2": "NON_PARTICIPATING",
        "20": "NON_PARTICIPATING",
        "21": "NON_PARTICIPATING",
        "22": "NON_PARTICIPATING",
        "23": "NON_PARTICIPATING",
        "24": "NON_PARTICIPATING",
        "25": "NON_PARTICIPATING",
        "26": "NON_PARTICIPATING",
        "27": "SUCCESS",
        "28": "NON_PARTICIPATING",
        "29": "NON_PARTICIPATING",
        "3": "NON_PARTICIPATING",
        "30": "NON_PARTICIPATING",
        "31": "NON_PARTICIPATING",
        "32": "NON_PARTICIPATING",
        "33": "NON_PARTICIPATING",
        "34": "NON_PARTICIPATING",
        "35": "NON_PARTICIPATING",
        "36": "SUCCESS",
        "37": "NON_PARTICIPATING",
        "38": "NON_PARTICIPATING",
        "39": "NON_PARTICIPATING",
        "4": "NON_PARTICIPATING",
        "40": "NON_PARTICIPATING",
        "41": "NON_PARTICIPATING",
        "42": "NON_PARTICIPATING",
        "43": "NON_PARTICIPATING",
        "5": "NON_PARTICIPATING",
        "6": "NON_PARTICIPATING",
        "7": "NON_PARTICIPATING",
        "8": "NON_PARTICIPATING",
        "9": "NON_PARTICIPATING"
    },
    "architectures": [
        "GPTOptim"
    ],
    "attn_pdrop": 0.1,
    "auto_map": {
        "AutoConfig": "configuration_gpt_optimized.GPTOptimConfig",
        "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
    },
    "block_size": 1024,
    "bos_token_id": 50256,
    "embd_pdrop": 0.1,
    "eos_token_id": 50256,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "model_type": "gpt_optimized",
    "n_embd": 1280,
    "n_head": 32,
    "n_inner": null,
    "n_layer": 48,
    "n_positions": 1024,
    "quantization_config": {
        "_load_in_4bit": false,
        "_load_in_8bit": true,
        "bnb_4bit_compute_dtype": "bfloat16",
        "bnb_4bit_quant_storage": "uint8",
        "bnb_4bit_quant_type": "fp4",
        "bnb_4bit_use_double_quant": false,
        "llm_int8_enable_fp32_cpu_offload": false,
        "llm_int8_has_fp16_weight": false,
        "llm_int8_skip_modules": [
            "lm_head"
        ],
        "llm_int8_threshold": 6.0,
        "load_in_4bit": false,
        "load_in_8bit": true,
        "quant_method": "bitsandbytes"
    },
    "reorder_and_upcast_attn": false,
    "resid_pdrop": 0.1,
    "scale_attn_by_inverse_layer_idx": false,
    "scale_attn_weights": true,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "vocab_size": 50257,
    "api_key": null
}