28 lines
714 B
JSON
28 lines
714 B
JSON
|
{
|
||
|
|
"_name_or_path": "/data/persuade/01_KuAlpaca/models/lora-alpaca-merged-ep5",
|
||
|
|
"architectures": [
|
||
|
|
"GPTNeoXForCausalLM"
|
||
|
|
],
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"classifier_dropout": 0.1,
|
||
|
|
"eos_token_id": 0,
|
||
|
|
"hidden_act": "gelu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 20480,
|
||
|
|
"layer_norm_eps": 1e-05,
|
||
|
|
"max_position_embeddings": 2048,
|
||
|
|
"model_type": "gpt_neox",
|
||
|
|
"num_attention_heads": 40,
|
||
|
|
"num_hidden_layers": 40,
|
||
|
|
"num_steps": "global_step301000",
|
||
|
|
"rotary_emb_base": 10000,
|
||
|
|
"rotary_pct": 0.5,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.29.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_parallel_residual": true,
|
||
|
|
"vocab_size": 30080
|
||
|
|
}
|