37 lines
927 B
JSON
37 lines
927 B
JSON
{
|
|
"activation_function": "gelu",
|
|
"apply_query_key_layer_scaling": true,
|
|
"architectures": [
|
|
"GPT2LMHeadModel"
|
|
],
|
|
"attn_pdrop": 0.1,
|
|
"bos_token_id": 2,
|
|
"dtype": "bfloat16",
|
|
"embd_pdrop": 0.1,
|
|
"eos_token_id": 3,
|
|
"initializer_range": 0.023,
|
|
"layer_norm_epsilon": 1e-05,
|
|
"model_type": "gpt2",
|
|
"n_ctx": 4096,
|
|
"n_embd": 768,
|
|
"n_head": 12,
|
|
"n_inner": 3072,
|
|
"n_layer": 12,
|
|
"n_positions": 4096,
|
|
"normalize_attention_scores": true,
|
|
"pad_token_id": 0,
|
|
"reorder_and_upcast_attn": false,
|
|
"resid_pdrop": 0.1,
|
|
"scale_attn_by_inverse_layer_idx": false,
|
|
"scale_attn_weights": true,
|
|
"summary_activation": null,
|
|
"summary_first_dropout": 0.1,
|
|
"summary_proj_to_labels": true,
|
|
"summary_type": "cls_index",
|
|
"summary_use_proj": true,
|
|
"tokenizer_class": "GPTSw3Tokenizer",
|
|
"transformers_version": "4.57.1",
|
|
"use_cache": false,
|
|
"vocab_size": 64016,
|
|
"max_position_embeddings": 4096
|
|
} |