38 lines
942 B
JSON
38 lines
942 B
JSON
{
|
|
"architectures": [
|
|
"KORMoForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "_configuration_kormo.KORMoConfig",
|
|
"AutoModel": "_modeling_kormo.KORMoModel",
|
|
"AutoModelForCausalLM": "_modeling_kormo.KORMoForCausalLM"
|
|
},
|
|
"bos_token_id": 125030,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 125031,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 16384,
|
|
"mask_type": null,
|
|
"max_position_embeddings": 131072,
|
|
"mlp_bias": false,
|
|
"model_type": "kormo",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"pretrain_tp": 1,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 500000.0,
|
|
"tie_word_embeddings": false,
|
|
"tie_word_embeddins": false,
|
|
"transformers_version": "4.57.0",
|
|
"use_cache": true,
|
|
"vocab_size": 125184
|
|
}
|