Files
Apertus-1.7B-wnorm2both/config.json

34 lines
754 B
JSON
Raw Normal View History

{
"architectures": [
"ApertusForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"hidden_act": "xielu",
"hidden_dropout": 0.0,
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "apertus",
"num_attention_heads": 32,
"num_hidden_layers": 16,
"num_key_value_heads": 8,
"pad_token_id": 3,
"post_norm": false,
"qk_norm": true,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 500000.0,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.7.0",
"use_cache": true,
"vocab_size": 131072
}