初始化项目，由ModelHub XC社区提供模型

Model: withU/kogpt2-emotion-chatbot
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
+*.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
+*.wasm 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 +1,24 @@
+# KoGPT2-emotion-chatbot
+kogpt2 on hugging face Transformers for Psychological Counseling
+- [full project link](https://github.com/jiminAn/Capstone_2022)
+
+## how to use
+```
+from transformers import GPT2LMHeadModel, PreTrainedTokenizerFast
+
+model = GPT2LMHeadModel.from_pretrained("withU/kogpt2-emotion-chatbot")
+tokenizer = PreTrainedTokenizerFast.from_pretrained("withU/kogpt2-emotion-chatbot")
+
+input_ids = tokenizer.encode("안녕", add_special_tokens=False, return_tensors="pt")
+output_sequences = model.generate(input_ids=input_ids, do_sample=True, max_length=80, num_return_sequences=4)
+for generated_sequence in output_sequences:
+    generated_sequence = generated_sequence.tolist()
+    print("GENERATED SEQUENCE : {0}".format(tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)))
+```
+## dataset finetuned on
+- [wellness dataset](https://aihub.or.kr/opendata/keti-data/recognition-laguage/KETI-02-006)
+- [emotion corpus of conversations](https://aihub.or.kr/opendata/keti-data/recognition-laguage/KETI-02-010)
+- [chatbot data](https://jeongukjae.github.io/tfds-korean/datasets/korean_chatbot_qa_data.html)
+## references
+- [WelllnessConversation-LanguageModel](https://github.com/nawnoes/WellnessConversation-LanguageModel)
+- [KoGPT2: SKT-AI](https://github.com/SKT-AI/KoGPT2)

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "taeminlee/kogpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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,
+  "output_past": true,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b044f401d2effcaaff25baefca0724b1812911ce1e5a2ad3f8fa60c1b24a1422
+size 509612457

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "<unk>", "pad_token": "<pad>", "bos_token": "<s>", "eos_token": "</s>", "special_tokens_map_file": "/Users/elplaguister/.cache/huggingface/transformers/81bb172c5a6c70898d8a2e22cf133bb951e80e92f6f12d3bd4c6270bcfd8413f.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "name_or_path": "taeminlee/kogpt2", "tokenizer_class": "PreTrainedTokenizerFast"}