rockbot-scratch / config.json
bigjoedata's picture
Added artists trained longer
b2dcde1
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.0,
"bos_token_id": 0,
"embd_pdrop": 0.0,
"eos_token_id": 0,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 512,
"n_embd": 256,
"n_head": 8,
"n_inner": null,
"n_layer": 8,
"n_positions": 512,
"resid_pdrop": 0.0,
"summary_activation": null,
"summary_first_dropout": 0.0,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"transformers_version": "4.3.2",
"use_cache": true,
"vocab_size": 75000
}