32 lines
732 B
JSON
32 lines
732 B
JSON
|
{
|
||
|
|
"_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": 0.1,
|
||
|
|
"dtype": "float16",
|
||
|
|
"enable_bias": true,
|
||
|
|
"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": 6,
|
||
|
|
"pad_token_id": 1,
|
||
|
|
"prefix": "</s>",
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"transformers_version": "5.3.0",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 50304,
|
||
|
|
"word_embed_proj_dim": 2048
|
||
|
|
}
|