NeoLLM / config.json
KitsuVp's picture
Model save
91342c4 verified
{
"architectures": [
"NeoLLMForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.1,
"auto_map": {
"AutoConfig": "configuration_neollm.NeoLLMConfig",
"AutoModel": "modeling_neollm.NeoLLMModel",
"AutoModelForCausalLM": "modeling_neollm.NeoLLMForCausalLM"
},
"dropout_rate": 0.1,
"dtype": "bfloat16",
"eos_token_id": 151643,
"fan_ratio": 0.125,
"fan_ratio_ffn": 0.0625,
"head_dim": 64,
"hidden_act": "xielu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 1536,
"max_position_embeddings": 512,
"model_type": "neollm",
"num_attention_heads": 8,
"num_hidden_layers": 12,
"num_key_value_heads": 2,
"num_stack_heads": 4,
"pad_token_id": 151643,
"partial_rotary_factor": 0.25,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"partial_rotary_factor": 0.25,
"rope_theta": 10000.0,
"rope_type": "default"
},
"rope_theta": 10000.0,
"stack_d_model": 16,
"stack_slots": 24,
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"use_cache": false,
"use_stack": true,
"vocab_size": 151665
}