96abhishekarora's picture
Updated model with better training and evaluation. Test and val data included as pickle files. Older Legacy files were removed to avoid confusion.
79be72d
raw
history blame contribute delete
622 Bytes
{
"_name_or_path": "sentence-transformers/multi-qa-mpnet-base-dot-v1",
"architectures": [
"MPNetModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"eos_token_id": 2,
"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": "mpnet",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"relative_attention_num_buckets": 32,
"torch_dtype": "float32",
"transformers_version": "4.35.1",
"vocab_size": 30527
}