|
{ |
|
"_attn_implementation_autoset": true, |
|
"_name_or_path": "Ren-Wei/Safe-RLHF-SFT-mistral-7b", |
|
"architectures": [ |
|
"MistralForScore" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"do_normalize": false, |
|
"eos_token_id": 2, |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 32768, |
|
"mean": [ |
|
0.029040411114692688 |
|
], |
|
"model_type": "mistral", |
|
"momentum": 0.9, |
|
"normalizer_type": "ExponentialMovingAverage", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"pad_token_id": 32000, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 10000.0, |
|
"score_bias": true, |
|
"score_dim": 1, |
|
"score_type": "reward", |
|
"sliding_window": 4096, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.49.0", |
|
"use_cache": true, |
|
"var": [ |
|
2.804319381713867 |
|
], |
|
"vocab_size": 32001 |
|
} |
|
|