初始化项目，由ModelHub XC社区提供模型

Model: aariciah/gpt2-german-dutch-merge
Source: Original Platform

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+base_model: zhuojing-huang/gpt2-german-20k
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-german-dutch-merge
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gpt2-german-dutch-merge
+
+This model is a fine-tuned version of [zhuojing-huang/gpt2-german-20k](https://huggingface.co/zhuojing-huang/gpt2-german-20k) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0004
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 6103
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.22.1