Hamilton / configs /transformer_340M.json
ZhenbinWang's picture
Upload 25 files
9fb98d3 verified
raw
history blame contribute delete
440 Bytes
{
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"fuse_cross_entropy": true,
"fuse_norm": true,
"hidden_act": "swish",
"hidden_size": 1024,
"initializer_range": 0.02,
"max_position_embeddings": 8192,
"model_type": "transformer",
"num_heads": 16,
"num_hidden_layers": 24,
"norm_eps": 1e-06,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 32000
}