34 lines
820 B
JSON
34 lines
820 B
JSON
|
{
|
||
|
|
"_name_or_path": "./bertModel/cus-llama2-base",
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"decoder_start_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"forced_eos_token_id": 2,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 768,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 2560,
|
||
|
|
"mask_token_id": 4,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 12,
|
||
|
|
"num_hidden_layers": 12,
|
||
|
|
"num_key_value_heads": 12,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"position_encoding_2d": false,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 5000000.0,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.38.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 851
|
||
|
|
}
|