foraburton / config.json
boris's picture
New model from https://wandb.ai/wandb/huggingtweets/runs/zrto18xz
0afe5d1
raw
history blame contribute delete
908 Bytes
{
"_name_or_path": "gpt2",
"activation_function": "gelu_new",
"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": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"resid_pdrop": 0.1,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 160,
"min_length": 10,
"prefix": "<|endoftext|>",
"temperature": 1.0,
"top_p": 0.95
}
},
"transformers_version": "4.4.2",
"use_cache": true,
"vocab_size": 50257
}