初始化项目,由ModelHub XC社区提供模型

Model: fpadovani/hin-deva-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed455
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-25 04:04:20 +08:00
commit 55bd702e53
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 sha256:807b206d91f390f86a112f14527d6ce88d3432bb33d74e9f860f4d28a59a1fa8
size 78179408

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfcaf19975c97f71e439655d565d903913851d370dae18f2d9004139972a088e
size 14709

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 sha256:0f9b30eb051bcc225cd21509e1fea75c68301b626855447a79abc7b0d0ad8da4
size 6353