39 lines
934 B
JSON
39 lines
934 B
JSON
{
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": true,
|
|
"attention_dropout": 0.00662607015,
|
|
"bos_token_id": 8001,
|
|
"dtype": "float32",
|
|
"eos_token_id": 8002,
|
|
"head_dim": 40,
|
|
"hidden_act": "silu",
|
|
"hidden_dropout": 0.00662607015,
|
|
"hidden_size": 320,
|
|
"initializer_range": 0.0215816655,
|
|
"intermediate_size": 896,
|
|
"max_position_embeddings": 1024,
|
|
"mlp_bias": true,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 8,
|
|
"num_hidden_layers": 8,
|
|
"num_key_value_heads": 4,
|
|
"pad_token_id": 8000,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1.168034e-05,
|
|
"rope_parameters": {
|
|
"factor": 128.0,
|
|
"high_freq_factor": 4.0,
|
|
"low_freq_factor": 1.0,
|
|
"original_max_position_embeddings": 128,
|
|
"rope_theta": 12566.37061436,
|
|
"rope_type": "llama3",
|
|
"type": "llama3"
|
|
},
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "5.0.0",
|
|
"use_cache": false,
|
|
"vocab_size": 8766
|
|
}
|