初始化项目,由ModelHub XC社区提供模型

Model: fpadovani/hin-deva-10mb-after-ppt-Dp-100mb-ckpt500_seed3407
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-10 05:50:13 +08:00
commit 374d25c765
360 changed files with 4266295 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": 512,
"n_head": 8,
"n_inner": 2048,
"n_layer": 4,
"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 sha256:78ecff1905664d152e3bdaff5eb4f47e2b5af4a04b7b4acdf898e915ff773fdd
size 78179408

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5d0a7a863dac9a9f72b65ba89fbf9884cbd817202fd000aeb843e41894f1472f
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:cfcecb41352908b2a034dc4ec11e511d1a7ed2d594a679147bc9b51bfe6bd14a
size 1500527

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:d443d3217c6ec3d8d199a4145874898a4a97f8fb81e56a97e58b4b8253fd9530
size 6353