mrm8488's picture
Training in progress, step 500
86d95c3
raw
history blame
664 Bytes
{
"_name_or_path": "microsoft/BioGPT-Large",
"activation_dropout": 0.0,
"architectures": [
"BioGptForCausalLM"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1600,
"initializer_range": 0.02,
"intermediate_size": 6400,
"layer_norm_eps": 1e-12,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "biogpt",
"num_attention_heads": 25,
"num_hidden_layers": 48,
"pad_token_id": 1,
"scale_embedding": true,
"torch_dtype": "float32",
"transformers_version": "4.28.1",
"use_cache": false,
"vocab_size": 57717
}