softpick-340M-4096-batch16-steps100000 / configs /softpick_transformer_120M.json
zaydzuhri's picture
Add files using upload-large-folder tool
0298ad2 verified
raw
history blame contribute delete
479 Bytes
{
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"fuse_cross_entropy": true,
"fuse_norm": false,
"hidden_act": "swish",
"hidden_size": 768,
"initializer_range": 0.02,
"max_position_embeddings": 4096,
"model_type": "transformer",
"num_heads": 12,
"num_hidden_layers": 14,
"norm_eps": 1e-06,
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 32000,
"attn_impl": "naive_softpick_attn"
}