初始化项目,由ModelHub XC社区提供模型

Model: fpadovani/nld-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-05 15:03:19 +08:00
commit 4f896eeaf6
229 changed files with 563225 additions and 0 deletions

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,34 @@
{
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50000,
"dtype": "bfloat16",
"embd_pdrop": 0.1,
"eos_token_id": 50001,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 512,
"n_embd": 768,
"n_head": 12,
"n_inner": 3072,
"n_layer": 12,
"n_positions": 512,
"pad_token_id": 50002,
"prefix": "[CLS]",
"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,
"transformers_version": "4.56.2",
"use_cache": true,
"vocab_size": 51200
}

View File

@@ -0,0 +1,9 @@
{
"_from_model_config": true,
"bos_token_id": 50000,
"eos_token_id": [
50001
],
"pad_token_id": 50002,
"transformers_version": "4.56.2"
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4daf5b055d5f9adbd67e17a65cf1b6454a53c684e60fb9c1cc9d6a203640b82a
size 249556672

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15e8c8caf4ab7c0db0d801a1848e4d4718a26158bb0173dac365820ce1ec0844
size 14645

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e1439ddd4efd41bbb4037b0a43943f5f0bc6fcce3f99741c34981fecc02d4bf
size 1156640

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a3f695d0bea707435808e5c35b01531888a7f55e6b907fd48cd8b86f2eca572
size 6353