ko-dialogpt-test-version

README.md

@@ -0,0 +1,33 @@
+---
+language: ko
+tags:
+  - gpt2
+  - conversational
+license: cc-by-nc-sa 4.0
+---
+## Ko-DialoGPT
+
+
+### How to use
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")
+
+for step in range(5):
+	# encode the new user input, add the eos_token and return a tensor in Pytorch
+	new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
+	# append the new user input tokens to the chat history
+	bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
+	# generated a response while limiting the total chat history to 1000 tokens,
+	chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+	# pretty print last ouput tokens from bot
+	print("BOT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
+```
+
+### Reference
+* [SKT-KoGPT2](https://huggingface.co/skt/kogpt2-base-v2)
+* [KETI R&D 데이터](https://aihub.or.kr/opendata/keti-data/recognition-laguage/KETI-02-008)
+* [한국어 대화 요약](https://aihub.or.kr/aidata/30714)

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "author": "Heewon Jeon(madjakarta@gmail.com)",
+  "bos_token_id": 0,
+  "created_date": "2021-04-28",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "license": "CC-BY-NC-SA 4.0",
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 3,
+  "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,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "transformers_version": "4.8.1",
+  "use_cache": true,
+  "vocab_size": 51200
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e11fe9d1a801b2d192e27950a43f8e6b12a5f7a389d682a64bc2804087a8f5
+size 513305211

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 @@
+{"special_tokens_map_file": "../base_model/kogpt2-base-v2/special_tokens_map.json", "name_or_path": "ko-dialogpt-대화요약", "tokenizer_class": "PreTrainedTokenizerFast"}