27 lines
660 B
JSON
27 lines
660 B
JSON
{
|
|
"architectures": [
|
|
"OpenLlamaForCausalLM"
|
|
],
|
|
"attention_dropout_prob": 0.1,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 5120,
|
|
"initializer_range": 1e-2,
|
|
"intermediate_size": 13824,
|
|
"max_position_embeddings": 2048,
|
|
"model_type": "open-llama",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 40,
|
|
"pad_token_id": 32000,
|
|
"rms_norm_eps": 1e-05,
|
|
"shared_input_output_embedding": false,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"use_cache": true,
|
|
"use_memorry_efficient_attention": true,
|
|
"use_stable_embedding": false,
|
|
"vocab_size": 68762
|
|
}
|