first commit

app.py

@@ -0,0 +1,63 @@
+
+
+import numpy as np
+#import itertools
+
+import gradio as gr
+
+import pandas as pd
+
+# make function using import pip to install torch
+import pip
+#pip.main(['install', 'torch'])
+#pip.main(['install', 'transformers'])
+
+import torch
+import transformers
+
+
+# saved_model
+def load_model():
+
+    pretrained_model_name = "skt/kogpt2-base-v2"
+
+    tokenizer = transformers.PreTrainedTokenizerFast.from_pretrained(
+        pretrained_model_name, # kogpt2
+        # kogpt는 사전에 토큰을 지정해주지 않으면, None 값으로 반영되어있음
+        # 반드시 지정해주어야 함
+        bos_token='</s>', eos_token='</s>', unk_token='<unk>',
+        pad_token='<pad>', mask_token='<mask>'
+        )
+    model = transformers.GPT2LMHeadModel.from_pretrained(
+            pretrained_model_name # kogpt2
+            )
+    model.resize_token_embeddings( len(tokenizer) )
+
+    return model, tokenizer
+
+
+# main
+def inference(prompt):
+
+    model, tokenizer = load_model()
+
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+    gen_ids = model.generate(input_ids,
+                           max_length=128,
+                           repetition_penalty=2.0,
+                           pad_token_id=tokenizer.pad_token_id,
+                           eos_token_id=tokenizer.eos_token_id,
+                           bos_token_id=tokenizer.bos_token_id,
+                           use_cache=True)
+    outputs = tokenizer.decode(gen_ids[0])
+
+    return outputs
+
+
+demo = gr.Interface(
+    fn=inference, 
+    inputs="text", 
+    outputs="text" #return 값
+    ).launch() # launch(share=True)를 설정하면 외부에서 접속 가능한 링크가 생성됨
+
+demo.launch()

gpt_model/config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "skt/kogpt2-base-v2",
+  "_num_labels": 1,
+  "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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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,
+  "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": "4.12.5",
+  "use_cache": true,
+  "vocab_size": 51200
+}

gpt_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1347fc29e6015fe4da9fbcf6770c1a962f201eeeea15391bf943fe62f46ee4ae
+size 513298281