31 lines
888 B
JSON
31 lines
888 B
JSON
{
|
|
"_remove_final_layer_norm": false,
|
|
"activation_dropout": 0.0,
|
|
"activation_function": "relu",
|
|
"antemplate": "[Genre: <|>]",
|
|
"architectures": [
|
|
"OPTForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 2,
|
|
"do_layer_norm_before": true,
|
|
"dropout": 0.1,
|
|
"eos_token_id": 2,
|
|
"ffn_dim": 10240,
|
|
"hidden_size": 2560,
|
|
"init_std": 0.02,
|
|
"layerdrop": 0.0,
|
|
"max_position_embeddings": 2048,
|
|
"model_type": "opt",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"pad_token_id": 1,
|
|
"prefix": "</s>",
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.24.0",
|
|
"use_cache": false,
|
|
"vocab_size": 50265,
|
|
"welcome": "\n\nYou are currently running the model `OPT-2.7B-Nerybus-Mix`\n\nThis is an experimental model containing a parameter-wise 50/50 blend (weighted average) of NerysV2-2.7B and ErebusV1-2.7B\n\n",
|
|
"word_embed_proj_dim": 2560
|
|
}
|