30 lines
871 B
JSON
30 lines
871 B
JSON
{
|
|
"_name_or_path": "/content/drive/MyDrive/Colab Notebooks/g_dl/dl_nlp/RLHF_3_DPO/3_\uc2e4\uc804\ud504\ub85c\uc81d\ud2b8_\uc2ec\ub9ac\uc0c1\ub2f4\uc0ac_2_mncai/model/sft/peftmodel_merged/5_single60366_seq1024",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 13824,
|
|
"max_position_embeddings": 2048,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 40,
|
|
"pad_token_id": 0,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.36.2",
|
|
"use_cache": false,
|
|
"vocab_size": 46336
|
|
}
|