{ "_name_or_path": "distributed/optimized-gpt2-2b", "activation_function": "gelu_new", "all_reduce_scores": { "0": "SUCCESS", "1": "SUCCESS", "10": "SUCCESS", "100": "SUCCESS", "101": "SUCCESS", "102": "SUCCESS", "103": "SUCCESS", "104": "SUCCESS", "105": "SUCCESS", "106": "SUCCESS", "107": "SUCCESS", "108": "SUCCESS", "109": "SUCCESS", "11": "SUCCESS", "110": "SUCCESS", "111": "SUCCESS", "112": "SUCCESS", "113": "SUCCESS", "114": "SUCCESS", "115": "SUCCESS", "116": "SUCCESS", "117": "SUCCESS", "118": "SUCCESS", "119": "SUCCESS", "12": "SUCCESS", "120": "SUCCESS", "121": "SUCCESS", "122": "SUCCESS", "123": "SUCCESS", "124": "SUCCESS", "125": "SUCCESS", "126": "SUCCESS", "127": "SUCCESS", "128": "SUCCESS", "129": "SUCCESS", "13": "SUCCESS", "130": "SUCCESS", "131": "SUCCESS", "132": "SUCCESS", "133": "SUCCESS", "134": "SUCCESS", "135": "SUCCESS", "136": "SUCCESS", "137": "SUCCESS", "138": "SUCCESS", "139": "SUCCESS", "14": "SUCCESS", "140": "SUCCESS", "141": "SUCCESS", "142": "SUCCESS", "143": "SUCCESS", "144": "SUCCESS", "145": "SUCCESS", "146": "SUCCESS", "147": "SUCCESS", "148": "SUCCESS", "149": "SUCCESS", "15": "SUCCESS", "150": "SUCCESS", "151": "SUCCESS", "152": "SUCCESS", "153": "SUCCESS", "154": "SUCCESS", "155": "SUCCESS", "156": "SUCCESS", "157": "SUCCESS", "158": "SUCCESS", "159": "SUCCESS", "16": "SUCCESS", "160": "SUCCESS", "161": "SUCCESS", "162": "SUCCESS", "163": "SUCCESS", "164": "SUCCESS", "165": "SUCCESS", "166": "SUCCESS", "167": "SUCCESS", "168": "SUCCESS", "169": "SUCCESS", "17": "SUCCESS", "170": "SUCCESS", "171": "SUCCESS", "172": "SUCCESS", "173": "SUCCESS", "174": "SUCCESS", "175": "SUCCESS", "176": "SUCCESS", "177": "SUCCESS", "178": "SUCCESS", "179": "SUCCESS", "18": "SUCCESS", "180": "SUCCESS", "181": "SUCCESS", "182": "SUCCESS", "183": "SUCCESS", "184": "SUCCESS", "185": "SUCCESS", "186": "SUCCESS", "187": "SUCCESS", "188": "SUCCESS", "189": "SUCCESS", "19": "SUCCESS", "190": "SUCCESS", "191": "SUCCESS", "192": "SUCCESS", "193": "SUCCESS", "194": "SUCCESS", "195": "SUCCESS", "196": "SUCCESS", "197": "SUCCESS", "198": "SUCCESS", "199": "SUCCESS", "2": "SUCCESS", "20": "SUCCESS", "200": "SUCCESS", "201": "SUCCESS", "202": "SUCCESS", "203": "SUCCESS", "204": "SUCCESS", "205": "SUCCESS", "206": "SUCCESS", "207": "SUCCESS", "208": "SUCCESS", "209": "SUCCESS", "21": "SUCCESS", "210": "SUCCESS", "211": "SUCCESS", "212": "SUCCESS", "213": "SUCCESS", "214": "SUCCESS", "215": "SUCCESS", "216": "SUCCESS", "217": "SUCCESS", "218": "SUCCESS", "219": "SUCCESS", "22": "SUCCESS", "220": "SUCCESS", "221": "SUCCESS", "222": "SUCCESS", "223": "SUCCESS", "224": "SUCCESS", "225": "SUCCESS", "226": "SUCCESS", "227": "SUCCESS", "228": "SUCCESS", "229": "SUCCESS", "23": "SUCCESS", "230": "SUCCESS", "231": "SUCCESS", "232": "SUCCESS", "233": "SUCCESS", "234": "SUCCESS", "235": "SUCCESS", "236": "SUCCESS", "237": "SUCCESS", "238": "SUCCESS", "239": "SUCCESS", "24": "SUCCESS", "240": "SUCCESS", "241": "SUCCESS", "242": "SUCCESS", "243": "SUCCESS", "244": "SUCCESS", "245": "SUCCESS", "246": "SUCCESS", "247": "SUCCESS", "248": "SUCCESS", "249": "SUCCESS", "25": "SUCCESS", "250": "SUCCESS", "251": "SUCCESS", "252": "SUCCESS", "253": "SUCCESS", "254": "SUCCESS", "255": "SUCCESS", "26": "SUCCESS", "27": "SUCCESS", "28": "SUCCESS", "29": "SUCCESS", "3": "SUCCESS", "30": "SUCCESS", "31": "SUCCESS", "32": "SUCCESS", "33": "SUCCESS", "34": "SUCCESS", "35": "SUCCESS", "36": "SUCCESS", "37": "SUCCESS", "38": "SUCCESS", "39": "SUCCESS", "4": "SUCCESS", "40": "SUCCESS", "41": "SUCCESS", "42": "SUCCESS", "43": "SUCCESS", "44": "SUCCESS", "45": "SUCCESS", "46": "SUCCESS", "47": "SUCCESS", "48": "SUCCESS", "49": "SUCCESS", "5": "SUCCESS", "50": "SUCCESS", "51": "SUCCESS", "52": "SUCCESS", "53": "SUCCESS", "54": "SUCCESS", "55": "SUCCESS", "56": "SUCCESS", "57": "SUCCESS", "58": "SUCCESS", "59": "SUCCESS", "6": "SUCCESS", "60": "SUCCESS", "61": "SUCCESS", "62": "SUCCESS", "63": "SUCCESS", "64": "SUCCESS", "65": "SUCCESS", "66": "SUCCESS", "67": "SUCCESS", "68": "SUCCESS", "69": "SUCCESS", "7": "SUCCESS", "70": "SUCCESS", "71": "SUCCESS", "72": "SUCCESS", "73": "SUCCESS", "74": "SUCCESS", "75": "SUCCESS", "76": "SUCCESS", "77": "SUCCESS", "78": "SUCCESS", "79": "SUCCESS", "8": "SUCCESS", "80": "SUCCESS", "81": "SUCCESS", "82": "SUCCESS", "83": "SUCCESS", "84": "SUCCESS", "85": "SUCCESS", "86": "SUCCESS", "87": "SUCCESS", "88": "SUCCESS", "89": "SUCCESS", "9": "SUCCESS", "90": "SUCCESS", "91": "SUCCESS", "92": "SUCCESS", "93": "SUCCESS", "94": "SUCCESS", "95": "SUCCESS", "96": "SUCCESS", "97": "SUCCESS", "98": "SUCCESS", "99": "SUCCESS" }, "architectures": [ "GPTOptim" ], "attn_pdrop": 0.1, "auto_map": { "AutoConfig": "distributed/optimized-gpt2-500m--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": 1904, "n_head": 34, "n_inner": null, "n_layer": 44, "n_positions": 1024, "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": "float32", "transformers_version": "4.39.3", "use_cache": true, "vocab_size": 50257 }