watashiha-gpt-6b / config.json
tatuRD
initial commit
8feb58a
{
"_name_or_path": "./watashiha-gpt-6b",
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.0,
"bos_token_id": 44879,
"embd_pdrop": 0.0,
"eos_token_id": 44879,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 4096,
"n_head": 32,
"n_inner": 16384,
"n_layer": 28,
"n_positions": 2048,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.0,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"tokenizer_class": "T5Tokenizer",
"torch_dtype": "bfloat16",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 44880
}