初始化项目，由ModelHub XC社区提供模型

Model: NYTK/PULI-GPT-2
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,62 @@
+---
+language:
+- hu
+tags:
+- text-generation
+- puli
+license: cc-by-nc-4.0
+widget:
+- text: Elmesélek egy történetet a nyelvtechnológiáról.
+---
+
+# PULI GPT-2
+
+For further details, see [our demo site](https://juniper.nytud.hu/demo/gpt2).
+
+  - Hungarian GPT-2 model
+  - Trained with Megatron-DeepSpeed [github](https://github.com/microsoft/Megatron-DeepSpeed)
+  - Dataset: 36.3 billion words
+  - Checkpoint: 500 000 steps
+
+## Limitations
+
+- max_seq_length = 1024
+
+
+## Citation
+If you use this model, please cite the following paper:
+
+```
+@inproceedings {yang-puli,
+    title = {Jönnek a nagyok! BERT-Large, GPT-2 és GPT-3 nyelvmodellek magyar nyelvre},
+	booktitle = {XIX. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2023)},
+	year = {2023},
+	publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
+	address = {Szeged, Hungary},
+	author = {Yang, Zijian Győző and Dodé, Réka and Ferenczi, Gergő and Héja, Enikő and Jelencsik-Mátyus, Kinga and Kőrös, Ádám and Laki, László János and Ligeti-Nagy, Noémi and Vadász, Noémi and Váradi, Tamás},
+	pages = {247--262}
+}
+```
+
+## Usage
+
+```python
+from transformers import GPT2Tokenizer, GPT2Model
+
+tokenizer = GPT2Tokenizer.from_pretrained('NYTK/PULI-GPT-2')
+model = GPT2Model.from_pretrained('NYTK/PULI-GPT-2')
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+
+```
+## Usage with pipeline
+
+```python
+from transformers import pipeline
+
+prompt = "Elmesélek egy történetet a nyelvtechnológiáról."
+generator = pipeline(task="text-generation", model="NYTK/PULI-GPT-2")
+
+print(generator(prompt)[0]["generated_text"])
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_fast",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 7,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 7,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": 4096,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "transformers_version": "4.16.2",
+  "use_cache": true,
+  "vocab_size": 50048
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e10f107f0e806efca81f017f2773ab55165a98abf4201e54703c07c6380fa5
+size 1468871833

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "/home/yanggy/CORPORA/PULI/corpora/vocab/GPT-vocab/25B/autovocab", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}