37 lines
847 B
JSON
37 lines
847 B
JSON
|
|
{
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 3,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 4,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 1024,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 4096,
|
||
|
|
"max_position_embeddings": 65536,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 16,
|
||
|
|
"num_hidden_layers": 18,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_parameters": {
|
||
|
|
"factor": 16.0,
|
||
|
|
"high_freq_factor": 4.0,
|
||
|
|
"low_freq_factor": 1.0,
|
||
|
|
"original_max_position_embeddings": 4096,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"rope_type": "llama3"
|
||
|
|
},
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"transformers_version": "5.10.2",
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 32768
|
||
|
|
}
|