gpt2-walamakan / config.json
Karzan's picture
End of training
d80e833
raw
history blame contribute delete
789 Bytes
{
"_name_or_path": "Karzan/gpt2-walamakan",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 0,
"embd_pdrop": 0.1,
"eos_token_id": 0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-06,
"model_type": "gpt2",
"n_embd": 768,
"n_head": 8,
"n_inner": null,
"n_layer": 10,
"n_positions": 1024,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": "tanh",
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.32.0",
"use_cache": true,
"vocab_size": 184789
}