33 lines
838 B
JSON
33 lines
838 B
JSON
|
{
|
||
|
|
"_name_or_path": "/home/jiaojianzhao/project/DeepSpeed-Chat/training/step3_rlhf_finetuning/output/actor",
|
||
|
|
"_remove_final_layer_norm": false,
|
||
|
|
"activation_dropout": 0.0,
|
||
|
|
"activation_function": "relu",
|
||
|
|
"architectures": [
|
||
|
|
"OPTForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 2,
|
||
|
|
"do_layer_norm_before": true,
|
||
|
|
"dropout": 0.0,
|
||
|
|
"enable_bias": true,
|
||
|
|
"end_token_id": 2,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"ffn_dim": 8192,
|
||
|
|
"hidden_size": 2048,
|
||
|
|
"init_std": 0.02,
|
||
|
|
"layer_norm_elementwise_affine": true,
|
||
|
|
"layerdrop": 0.0,
|
||
|
|
"max_position_embeddings": 2048,
|
||
|
|
"model_type": "opt",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 24,
|
||
|
|
"pad_token_id": 2,
|
||
|
|
"prefix": "</s>",
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.29.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 50272,
|
||
|
|
"word_embed_proj_dim": 2048
|
||
|
|
}
|