Doron Adler
"pad_token_id": 50256
316f27f
{
"_name_or_path": "/content/trained_model",
"activation_function": "gelu_new",
"architectures": [
"GPTNeoForCausalLM"
],
"attention_dropout": 0,
"attention_layers": [
"global",
"global",
"global",
"global",
"global",
"global",
"global",
"global",
"global",
"global",
"global",
"global"
],
"attention_types": [
[
[
"global"
],
12
]
],
"bos_token_id": 50256,
"pad_token_id": 50256,
"embed_dropout": 0,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": null,
"layer_norm_epsilon": 1e-05,
"line_by_line": false,
"max_position_embeddings": 2048,
"model_type": "gpt_neo",
"num_heads": 12,
"num_layers": 12,
"resid_dropout": 0,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"transformers_version": "4.9.0.dev0",
"use_cache": true,
"vocab_size": 50257,
"window_size": 256
}