{ | |
"_name_or_path": "RLHFlow/ArmoRM-Llama3-8B-v0.1 ", | |
"auto_map": { | |
"AutoModelForSequenceClassification": "modeling_custom.LlamaForRewardModelWithGating" | |
}, | |
"architectures": [ | |
"LlamaForRewardModelWithGating" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 128000, | |
"eos_token_id": 128001, | |
"hidden_act": "silu", | |
"hidden_size": 4096, | |
"id2label": { | |
"0": "LABEL_0" | |
}, | |
"initializer_range": 0.02, | |
"intermediate_size": 14336, | |
"label2id": { | |
"LABEL_0": 0 | |
}, | |
"max_position_embeddings": 8192, | |
"model_type": "llama", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 32, | |
"num_key_value_heads": 8, | |
"pad_token_id": 128256, | |
"pretraining_tp": 1, | |
"rms_norm_eps": 1e-05, | |
"rope_scaling": null, | |
"rope_theta": 500000.0, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float32", | |
"transformers_version": "4.40.0", | |
"use_cache": false, | |
"vocab_size": 128257, | |
"num_objectives": 19, | |
"gating_temperature": 10, | |
"gating_hidden_dim": 1024, | |
"gating_n_hidden": 3 | |
} | |