{ "_name_or_path": "distributed/llama-1b", "all_reduce_scores": { "0": "NOT_ALIVE", "1": "NON_PARTICIPATING", "10": "FAIL", "100": "NOT_ALIVE", "101": "FAIL", "102": "FAIL", "103": "NOT_ALIVE", "104": "NOT_ALIVE", "105": "FAIL", "106": "FAIL", "107": "NON_PARTICIPATING", "108": "NON_PARTICIPATING", "109": "FAIL", "11": "FAIL", "110": "NON_PARTICIPATING", "111": "NOT_ALIVE", "112": "NON_PARTICIPATING", "113": "FAIL", "114": "FAIL", "115": "NON_PARTICIPATING", "116": "FAIL", "117": "NON_PARTICIPATING", "118": "FAIL", "119": "NON_PARTICIPATING", "12": "NON_PARTICIPATING", "120": "NOT_ALIVE", "121": "NOT_ALIVE", "122": "NON_PARTICIPATING", "123": "FAIL", "124": "NON_PARTICIPATING", "125": "NON_PARTICIPATING", "126": "FAIL", "127": "NON_PARTICIPATING", "128": "NON_PARTICIPATING", "129": "NON_PARTICIPATING", "13": "FAIL", "130": "NOT_ALIVE", "131": "NOT_ALIVE", "132": "NOT_ALIVE", "133": "NOT_ALIVE", "134": "NOT_ALIVE", "135": "NON_PARTICIPATING", "136": "NON_PARTICIPATING", "137": "NOT_ALIVE", "138": "NON_PARTICIPATING", "139": "NON_PARTICIPATING", "14": "NOT_ALIVE", "140": "NOT_ALIVE", "141": "NOT_ALIVE", "142": "FAIL", "143": "NOT_ALIVE", "144": "NON_PARTICIPATING", "145": "NOT_ALIVE", "146": "FAIL", "147": "FAIL", "148": "NON_PARTICIPATING", "149": "NON_PARTICIPATING", "15": "NON_PARTICIPATING", "150": "NOT_ALIVE", "151": "NOT_ALIVE", "152": "NOT_ALIVE", "153": "FAIL", "154": "FAIL", "155": "NOT_ALIVE", "156": "NON_PARTICIPATING", "157": "NON_PARTICIPATING", "158": "NON_PARTICIPATING", "159": "NON_PARTICIPATING", "16": "NOT_ALIVE", "160": "NOT_ALIVE", "161": "FAIL", "162": "NOT_ALIVE", "163": "FAIL", "164": "NOT_ALIVE", "165": "NOT_ALIVE", "166": "NON_PARTICIPATING", "167": "NON_PARTICIPATING", "168": "NON_PARTICIPATING", "169": "NON_PARTICIPATING", "17": "NON_PARTICIPATING", "170": "FAIL", "171": "FAIL", "172": "NOT_ALIVE", "173": "NON_PARTICIPATING", "174": "NOT_ALIVE", "175": "NON_PARTICIPATING", "176": "NOT_ALIVE", "177": "NON_PARTICIPATING", "178": "NOT_ALIVE", "179": "NOT_ALIVE", "18": "NOT_ALIVE", "180": "NOT_ALIVE", "181": "NOT_ALIVE", "182": "NON_PARTICIPATING", "183": "FAIL", "184": "FAIL", "185": "FAIL", "186": "NON_PARTICIPATING", "187": "NON_PARTICIPATING", "188": "NOT_ALIVE", "189": "NOT_ALIVE", "19": "NON_PARTICIPATING", "190": "NON_PARTICIPATING", "191": "NOT_ALIVE", "192": "NON_PARTICIPATING", "193": "NOT_ALIVE", "194": "NOT_ALIVE", "195": "NOT_ALIVE", "196": "FAIL", "197": "NON_PARTICIPATING", "198": "FAIL", "199": "NOT_ALIVE", "2": "NON_PARTICIPATING", "20": "FAIL", "200": "FAIL", "201": "NOT_ALIVE", "202": "NON_PARTICIPATING", "203": "NON_PARTICIPATING", "204": "NOT_ALIVE", "205": "FAIL", "206": "FAIL", "207": "NOT_ALIVE", "208": "NON_PARTICIPATING", "209": "NON_PARTICIPATING", "21": "FAIL", "210": "NON_PARTICIPATING", "211": "FAIL", "212": "NOT_ALIVE", "213": "NOT_ALIVE", "214": "NOT_ALIVE", "215": "NOT_ALIVE", "216": "NOT_ALIVE", "217": "NOT_ALIVE", "218": "NOT_ALIVE", "219": "NOT_ALIVE", "22": "NOT_ALIVE", "220": "NON_PARTICIPATING", "221": "FAIL", "222": "FAIL", "223": "NOT_ALIVE", "224": "NOT_ALIVE", "225": "NON_PARTICIPATING", "226": "NON_PARTICIPATING", "227": "NON_PARTICIPATING", "228": "NON_PARTICIPATING", "229": "FAIL", "23": "NON_PARTICIPATING", "230": "FAIL", "231": "NON_PARTICIPATING", "232": "FAIL", "233": "NON_PARTICIPATING", "234": "NON_PARTICIPATING", "235": "FAIL", "236": "NON_PARTICIPATING", "237": "FAIL", "238": "NON_PARTICIPATING", "239": "NON_PARTICIPATING", "24": "NON_PARTICIPATING", "240": "NOT_ALIVE", "241": "FAIL", "242": "NOT_ALIVE", "243": "NOT_ALIVE", "244": "NOT_ALIVE", "245": "FAIL", "246": "FAIL", "247": "NOT_ALIVE", "248": "NON_PARTICIPATING", "249": "NOT_ALIVE", "25": "NOT_ALIVE", "250": "NON_PARTICIPATING", "251": "NOT_ALIVE", "252": "NON_PARTICIPATING", "253": "NOT_ALIVE", "254": "NON_PARTICIPATING", "255": "FAIL", "26": "FAIL", "27": "NOT_ALIVE", "28": "FAIL", "29": "NOT_ALIVE", "3": "NOT_ALIVE", "30": "NON_PARTICIPATING", "31": "FAIL", "32": "NOT_ALIVE", "33": "NOT_ALIVE", "34": "NOT_ALIVE", "35": "FAIL", "36": "NOT_ALIVE", "37": "NON_PARTICIPATING", "38": "NON_PARTICIPATING", "39": "NON_PARTICIPATING", "4": "NON_PARTICIPATING", "40": "NON_PARTICIPATING", "41": "NOT_ALIVE", "42": "NON_PARTICIPATING", "43": "NOT_ALIVE", "44": "NON_PARTICIPATING", "45": "NON_PARTICIPATING", "46": "NON_PARTICIPATING", "47": "NON_PARTICIPATING", "48": "NOT_ALIVE", "49": "NOT_ALIVE", "5": "NOT_ALIVE", "50": "FAIL", "51": "NON_PARTICIPATING", "52": "NON_PARTICIPATING", "53": "NON_PARTICIPATING", "54": "NOT_ALIVE", "55": "NOT_ALIVE", "56": "NON_PARTICIPATING", "57": "FAIL", "58": "NOT_ALIVE", "59": "NON_PARTICIPATING", "6": "NOT_ALIVE", "60": "FAIL", "61": "NOT_ALIVE", "62": "NON_PARTICIPATING", "63": "NON_PARTICIPATING", "64": "FAIL", "65": "NON_PARTICIPATING", "66": "NOT_ALIVE", "67": "NON_PARTICIPATING", "68": "NOT_ALIVE", "69": "NON_PARTICIPATING", "7": "FAIL", "70": "NON_PARTICIPATING", "71": "NON_PARTICIPATING", "72": "NOT_ALIVE", "73": "NOT_ALIVE", "74": "NOT_ALIVE", "75": "NON_PARTICIPATING", "76": "NOT_ALIVE", "77": "NOT_ALIVE", "78": "NOT_ALIVE", "79": "NOT_ALIVE", "8": "NON_PARTICIPATING", "80": "NON_PARTICIPATING", "81": "NOT_ALIVE", "82": "FAIL", "83": "NOT_ALIVE", "84": "FAIL", "85": "NON_PARTICIPATING", "86": "FAIL", "87": "FAIL", "88": "NOT_ALIVE", "89": "FAIL", "9": "NON_PARTICIPATING", "90": "FAIL", "91": "NON_PARTICIPATING", "92": "FAIL", "93": "NOT_ALIVE", "94": "NOT_ALIVE", "95": "NOT_ALIVE", "96": "FAIL", "97": "NOT_ALIVE", "98": "NON_PARTICIPATING", "99": "NON_PARTICIPATING" }, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "block_list": [ 6499121, 6499149 ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "inner_step": 36, "intermediate_size": 5632, "last_allreduce_block": 6498862, "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 }