初始化项目,由ModelHub XC社区提供模型

Model: cglez/gpt2-ag_news
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-30 19:21:46 +08:00
commit 5de9e6fb4d
16 changed files with 150540 additions and 0 deletions

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"_name_or_path": "output/pretrained_model/gpt2-ag_news/checkpoint-112500",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"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,
"torch_dtype": "float32",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 50257
}