cstorm125's picture
trained with chimera_qa
4d2b4a3
{
"_name_or_path": "airesearch/wangchanberta-base-wiki-20210520-news-spm_span-mask",
"architectures": [
"CamembertForQuestionAnswering"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "camembert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"transformers_version": "4.8.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 25005
}