初始化项目,由ModelHub XC社区提供模型

Model: ai-forever/rugpt3large_based_on_gpt2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-04 02:15:13 +08:00
commit 2f837878bc
10 changed files with 50201 additions and 0 deletions

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 1,
"embd_pdrop": 0.1,
"eos_token_id": 2,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 2048,
"n_embd": 1536,
"n_head": 16,
"n_inner": null,
"n_layer": 24,
"n_positions": 2048,
"pad_token_id": 0,
"resid_pdrop": 0.1,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"vocab_size": 50257
}