gpt2-xl-wechsel-german / config.json
malteos's picture
add model
2f64fbf
raw
history blame
965 Bytes
{
"_name_or_path": "/netscratch/mostendorff/experiments/oxw/data/gpt2-xl-wechsel-german/hf_checkpoints/global_step100000",
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 1600,
"n_head": 25,
"n_inner": 6400,
"n_layer": 48,
"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": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"tokenizer_class": "GPT2TokenizerFast",
"torch_dtype": "float32",
"transformers_version": "4.18.0",
"use_cache": true,
"vocab_size": 50304
}