{ "_name_or_path": "distributed/llama-1b", "all_reduce_scores": { "0": "NOT_ALIVE", "1": "FAIL", "10": "NON_PARTICIPATING", "100": "NOT_ALIVE", "101": "NOT_ALIVE", "102": "NOT_ALIVE", "103": "NON_PARTICIPATING", "104": "FAIL", "105": "NON_PARTICIPATING", "106": "NON_PARTICIPATING", "107": "NON_PARTICIPATING", "108": "NOT_ALIVE", "109": "FAIL", "11": "NON_PARTICIPATING", "110": "NOT_ALIVE", "111": "FAIL", "112": "NON_PARTICIPATING", "113": "NOT_ALIVE", "114": "NON_PARTICIPATING", "115": "NON_PARTICIPATING", "116": "NOT_ALIVE", "117": "NON_PARTICIPATING", "118": "NON_PARTICIPATING", "119": "NOT_ALIVE", "12": "NON_PARTICIPATING", "120": "NON_PARTICIPATING", "121": "NOT_ALIVE", "122": "FAIL", "123": "NON_PARTICIPATING", "124": "FAIL", "125": "NON_PARTICIPATING", "126": "NON_PARTICIPATING", "127": "FAIL", "128": "NOT_ALIVE", "129": "NON_PARTICIPATING", "13": "FAIL", "130": "NOT_ALIVE", "131": "NOT_ALIVE", "132": "NOT_ALIVE", "133": "NON_PARTICIPATING", "134": "NON_PARTICIPATING", "135": "NON_PARTICIPATING", "136": "NOT_ALIVE", "137": "NOT_ALIVE", "138": "NON_PARTICIPATING", "139": "NOT_ALIVE", "14": "NOT_ALIVE", "140": "NOT_ALIVE", "141": "NOT_ALIVE", "142": "NON_PARTICIPATING", "143": "NON_PARTICIPATING", "144": "NOT_ALIVE", "145": "NON_PARTICIPATING", "146": "FAIL", "147": "NON_PARTICIPATING", "148": "NOT_ALIVE", "149": "NON_PARTICIPATING", "15": "NON_PARTICIPATING", "150": "NON_PARTICIPATING", "151": "NOT_ALIVE", "152": "NOT_ALIVE", "153": "FAIL", "154": "NON_PARTICIPATING", "155": "NOT_ALIVE", "156": "FAIL", "157": "FAIL", "158": "NON_PARTICIPATING", "159": "NON_PARTICIPATING", "16": "NON_PARTICIPATING", "160": "NOT_ALIVE", "161": "NOT_ALIVE", "162": "FAIL", "163": "NOT_ALIVE", "164": "NOT_ALIVE", "165": "NON_PARTICIPATING", "166": "NON_PARTICIPATING", "167": "NOT_ALIVE", "168": "NON_PARTICIPATING", "169": "FAIL", "17": "FAIL", "170": "NON_PARTICIPATING", "171": "NOT_ALIVE", "172": "NOT_ALIVE", "173": "FAIL", "174": "NOT_ALIVE", "175": "NON_PARTICIPATING", "176": "NOT_ALIVE", "177": "NON_PARTICIPATING", "178": "NON_PARTICIPATING", "179": "NON_PARTICIPATING", "18": "FAIL", "180": "FAIL", "181": "FAIL", "182": "FAIL", "183": "NON_PARTICIPATING", "184": "NON_PARTICIPATING", "185": "NOT_ALIVE", "186": "FAIL", "187": "NOT_ALIVE", "188": "NOT_ALIVE", "189": "NOT_ALIVE", "19": "NON_PARTICIPATING", "190": "NON_PARTICIPATING", "191": "NOT_ALIVE", "192": "NON_PARTICIPATING", "193": "NON_PARTICIPATING", "194": "NON_PARTICIPATING", "195": "NON_PARTICIPATING", "196": "NON_PARTICIPATING", "197": "NON_PARTICIPATING", "198": "FAIL", "199": "FAIL", "2": "NON_PARTICIPATING", "20": "NON_PARTICIPATING", "200": "NON_PARTICIPATING", "201": "NOT_ALIVE", "202": "NON_PARTICIPATING", "203": "NON_PARTICIPATING", "204": "NOT_ALIVE", "205": "NOT_ALIVE", "206": "FAIL", "207": "NOT_ALIVE", "208": "NOT_ALIVE", "209": "FAIL", "21": "FAIL", "210": "FAIL", "211": "NON_PARTICIPATING", "212": "NON_PARTICIPATING", "213": "NOT_ALIVE", "214": "FAIL", "215": "NON_PARTICIPATING", "216": "FAIL", "217": "NON_PARTICIPATING", "218": "NOT_ALIVE", "219": "NON_PARTICIPATING", "22": "NON_PARTICIPATING", "220": "NOT_ALIVE", "221": "NON_PARTICIPATING", "222": "NOT_ALIVE", "223": "NON_PARTICIPATING", "224": "NOT_ALIVE", "225": "FAIL", "226": "NON_PARTICIPATING", "227": "FAIL", "228": "NON_PARTICIPATING", "229": "NOT_ALIVE", "23": "NON_PARTICIPATING", "230": "NOT_ALIVE", "231": "NON_PARTICIPATING", "232": "NON_PARTICIPATING", "233": "FAIL", "234": "FAIL", "235": "NON_PARTICIPATING", "236": "FAIL", "237": "NOT_ALIVE", "238": "NON_PARTICIPATING", "239": "NON_PARTICIPATING", "24": "NON_PARTICIPATING", "240": "NOT_ALIVE", "241": "NON_PARTICIPATING", "242": "NOT_ALIVE", "243": "NON_PARTICIPATING", "244": "NOT_ALIVE", "245": "NOT_ALIVE", "246": "FAIL", "247": "FAIL", "248": "NOT_ALIVE", "249": "NON_PARTICIPATING", "25": "SUCCESS", "250": "NON_PARTICIPATING", "251": "NON_PARTICIPATING", "252": "NON_PARTICIPATING", "253": "NON_PARTICIPATING", "254": "NON_PARTICIPATING", "255": "NON_PARTICIPATING", "26": "FAIL", "27": "FAIL", "28": "NON_PARTICIPATING", "29": "NON_PARTICIPATING", "3": "NON_PARTICIPATING", "30": "NON_PARTICIPATING", "31": "FAIL", "32": "NOT_ALIVE", "33": "NOT_ALIVE", "34": "NON_PARTICIPATING", "35": "NON_PARTICIPATING", "36": "NON_PARTICIPATING", "37": "NOT_ALIVE", "38": "FAIL", "39": "NON_PARTICIPATING", "4": "FAIL", "40": "NOT_ALIVE", "41": "NOT_ALIVE", "42": "NON_PARTICIPATING", "43": "NOT_ALIVE", "44": "FAIL", "45": "FAIL", "46": "NON_PARTICIPATING", "47": "FAIL", "48": "NON_PARTICIPATING", "49": "NON_PARTICIPATING", "5": "NON_PARTICIPATING", "50": "NON_PARTICIPATING", "51": "NOT_ALIVE", "52": "FAIL", "53": "NON_PARTICIPATING", "54": "NOT_ALIVE", "55": "NON_PARTICIPATING", "56": "FAIL", "57": "NON_PARTICIPATING", "58": "NOT_ALIVE", "59": "NON_PARTICIPATING", "6": "NOT_ALIVE", "60": "NON_PARTICIPATING", "61": "FAIL", "62": "NON_PARTICIPATING", "63": "NON_PARTICIPATING", "64": "NOT_ALIVE", "65": "NON_PARTICIPATING", "66": "NON_PARTICIPATING", "67": "NON_PARTICIPATING", "68": "NOT_ALIVE", "69": "FAIL", "7": "NOT_ALIVE", "70": "NON_PARTICIPATING", "71": "NOT_ALIVE", "72": "NON_PARTICIPATING", "73": "FAIL", "74": "FAIL", "75": "FAIL", "76": "FAIL", "77": "NOT_ALIVE", "78": "NOT_ALIVE", "79": "NON_PARTICIPATING", "8": "NON_PARTICIPATING", "80": "FAIL", "81": "NOT_ALIVE", "82": "NON_PARTICIPATING", "83": "NON_PARTICIPATING", "84": "FAIL", "85": "NON_PARTICIPATING", "86": "NOT_ALIVE", "87": "FAIL", "88": "NON_PARTICIPATING", "89": "NON_PARTICIPATING", "9": "NOT_ALIVE", "90": "NON_PARTICIPATING", "91": "FAIL", "92": "NON_PARTICIPATING", "93": "NOT_ALIVE", "94": "FAIL", "95": "NOT_ALIVE", "96": "NON_PARTICIPATING", "97": "NON_PARTICIPATING", "98": "NON_PARTICIPATING", "99": "NON_PARTICIPATING" }, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "block_list": [ 6454486, 6454516 ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "inner_step": 63, "intermediate_size": 5632, "last_allreduce_block": 6454064, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.39.3", "use_cache": false, "vocab_size": 32000 }