初始化项目，由ModelHub XC社区提供模型

Model: ytu-ce-cosmos/turkish-gpt2-large
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model_cover.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+datasets:
+- uonlp/CulturaX
+language:
+- tr
+pipeline_tag: text-generation
+
+tags:
+- Turkish
+- turkish
+- gpt2
+---
+
+<img src="./model_cover.png" width=400px/>
+
+# turkish-gpt2
+
+This is a Turkish GPT-2 large model. GPT-2 is designed for text generation tasks, providing the ability to continue a given text snippet in a coherent and contextually relevant manner.
+Due to the diverse nature of the training data, which includes websites, books, and other text sources, this model can exhibit biases. Users should be aware of these biases and use the model responsibly.
+
+## Example Usage
+```python
+from transformers import AutoTokenizer, GPT2LMHeadModel
+from transformers import pipeline
+
+model = GPT2LMHeadModel.from_pretrained("ytu-ce-cosmos/turkish-gpt2-large")
+tokenizer = AutoTokenizer.from_pretrained("ytu-ce-cosmos/turkish-gpt2-large")
+
+text_generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
+r = text_generator("Teknolojinin gelişimi hayatımızı önemli ölçüde etkiledi. ", max_length=100)
+[{'generated_text': 'Teknolojinin gelişimi hayatımızı önemli ölçüde etkiledi. "Sosyal ağ" adını verdiğimiz yeni bir iletişim çağımız oluştu. '}]
+
+```
+
+Relevant information can be found in the [paper](https://arxiv.org/abs/2404.17336).
+
+# Acknowledgments
+- Research supported with Cloud TPUs from [Google's TensorFlow Research Cloud](https://sites.research.google/trc/about/) (TFRC). Thanks for providing access to the TFRC ❤️
+- Thanks to the generous support from the Hugging Face team, it is possible to download models from their S3 storage 🤗
+
+# Citation
+```bibtex
+@article{kesgin2024introducing,
+  title={Introducing cosmosGPT: Monolingual Training for Turkish Language Models},
+  author={Kesgin, H Toprak and Yuce, M Kaan and Dogan, Eren and Uzun, M Egemen and Uz, Atahan and Seyrek, H Emre and Zeer, Ahmed and Amasyali, M Fatih},
+  journal={arXiv preprint arXiv:2404.17336},
+  year={2024}
+}
+```
+
+### Contact 
+COSMOS AI Research Group, Yildiz Technical University Computer Engineering Department   <br>
+https://cosmos.yildiz.edu.tr/ <br>
+cosmos@yildiz.edu.tr <br>

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "pad_token_id": 0,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9d81a8678b9f111604cdde0a176657a40ee5b5d31ec6b9483dda155b2a9945
+size 3096165928

model_cover.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0717747520d55a43f2a4caa2e91c3a0b5cc99d73c5d5f02066d21ae31f5cf54
+size 1509490

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a1de8359ab423a32ac02d51f011536e64a8cc09282358a0ee22371350b5e41
+size 3096256605

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4146bea8ae5ebd0fe8e89506ef42da588180d7a36a869b75807c06bd06f94ab6
+size 3096629608

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}