初始化项目，由ModelHub XC社区提供模型

Model: ULTR0N/SentienceTrial1
Source: Original Platform

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+language:
+- hu
+tags:
+- text-generation
+license: mit
+widget:
+- text: Szegeden, január végén,
+---
+
+# Hungarian GPT-2 poem generator in Petőfi style
+
+For further models, scripts and details, see [our repository](https://github.com/nytud/neural-models) or [our demo site](https://juniper.nytud.hu/demo/nlp).
+
+- Pretrained on Hungarian Wikipedia
+- Finetuned on Petőfi Sándor összes költeményei
+
+
+## Results
+
+| Model | Perplexity |
+| ------------- | ------------- |
+| **GPT-2 poem**  | **47.46** | 
+| GPT-2 news | 22.06 | 
+
+
+## Citation
+If you use this model, please cite the following paper:
+```
+@inproceedings {yang-gpt2,
+    title = {{"Az invazív medvék nem tolerálják a suzukis agressziót" - Magyar GPT-2 kísérleti modell}},
+	booktitle = {XVIII. Magyar Számítógépes Nyelvészeti Konferencia},
+	year = {2022},
+	publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
+	address = {Szeged, Magyarország},
+	author = {Yang, Zijian Győző},
+	pages = {463--476}
+}
+
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/data/users/fragata/GPT/models",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "use_cache": true,
+  "vocab_size": 33000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1ee7eb6bc13482f8a211f3bbf0e22b73b4f08711fd8670250e2c9b82aa1a2b
+size 457394811

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}

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, "errors": "replace", "special_tokens_map_file": null, "name_or_path": "/data/users/fragata/GPT/models", "tokenizer_class": "GPT2Tokenizer"}