File size: 1,092 Bytes
7e47d0d d68da6c 7e47d0d 6866673 3c7cdc7 25b164f 3c7cdc7 7e47d0d aa970ab 3c7cdc7 aa970ab 7e47d0d 3c7cdc7 7e47d0d 3c7cdc7 7e47d0d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | {
"_name_or_path": "distributed/llama-1b",
"all_reduce_scores": {
"0": "NOT_ALIVE",
"1": "NOT_ALIVE",
"10": "FAIL",
"11": "NOT_ALIVE",
"2": "NOT_ALIVE",
"3": "NOT_ALIVE",
"4": "NOT_ALIVE",
"5": "NOT_ALIVE",
"6": "NOT_ALIVE",
"7": "NOT_ALIVE",
"8": "NOT_ALIVE",
"9": "NOT_ALIVE"
},
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"block_list": [
6454776,
6454806
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"inner_step": 9,
"intermediate_size": 5632,
"last_allreduce_block": 5428935,
"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
}
|