Upload 4 files

README.md

@@ -0,0 +1,43 @@
+---
+license: cc-by-nc-sa-4.0
+datasets:
+- nlpai-lab/kullm-v2
+language:
+- ko
+pipeline_tag: text-generation
+---
+
+교육용으로 학습 한 간단한 instruction fine-tuning 모델 (updated 2023/08/06)
+
+- Pretrained model: skt/kogpt2-base-v2 (https://github.com/SKT-AI/KoGPT2)
+- Training data: kullm-v2(https://huggingface.co/datasets/nlpai-lab/kullm-v2)
+
+```python
+from transformers import AutoModelForCausalLM
+from transformers import PreTrainedTokenizerFast
+
+tokenizer = PreTrainedTokenizerFast.from_pretrained("hyunjae/skt-kogpt2-kullm-v2",
+                                                    bos_token='</s>', eos_token='</s>', unk_token='<unk>',
+                                                    pad_token='<pad>', mask_token='<mask>', padding_side="right", model_max_length=512)
+model = AutoModelForCausalLM.from_pretrained('hyunjae/skt-kogpt2-kullm-v2').to('cuda')
+
+PROMPT= "### system:사용자의 질문에 맞는 적절한 응답을 생성하세요.\n### 사용자:{instruction}\n### 응답:"
+text = PROMPT.format_map({'instruction':"안녕? 너가 할 수 있는게 뭐야?"})
+input_ids = tokenizer.encode(text, return_tensors='pt').to(model.device)
+
+gen_ids = model.generate(input_ids,
+                        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,
+                        num_beams=4,
+                        no_repeat_ngram_size=4,
+                        max_new_tokens=128,
+                        do_sample=True,
+                        top_k=50)
+
+
+generated = tokenizer.decode(gen_ids[0])
+print(generated)
+
+```

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([email protected])",
+  "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": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f96532ab2bee50085f6c06923f4ea3ac8d184b9efe67bf25a7088617d5f6f15
+size 500704093