Update README.md

README.md

@@ -1,6 +1,11 @@
 ---
 library_name: transformers
-tags: []
+datasets:
+- daekeun-ml/naver-news-summarization-ko
+language:
+- ko
+base_model:
+- google/gemma-2-9b-it
 ---
 
 # Model Card for Model ID
@@ -35,7 +40,47 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+```python
+from peft import PeftModel
+from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+
+MODEL_ID = "google/gemma-2-9b-it"
+PEFT_MODEL_ID = "drlee1/gemma2-9b-it-qdora-summary"
+
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map = 'auto', torch_dtype = torch.float16)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+model = PeftModel.from_pretrained(model, PEFT_MODEL_ID, device_map = 'auto', torch_dtype = torch.float16)
+
+pipe = pipeline("text-generation", model = model, tokenizer = tokenizer, max_new_tokens = 512)
+
+doc = "..."
+
+messages = [
+    {"role": "user", "content": "다음 글을 요약해주세요:\n\n{}".format(doc)}
+]
+
+prompt = tokenizer.apply_chat_template(messages, tokenize = False, add_generation_prompt = True)
+
+outputs = pipe(
+    prompt,
+    do_sample = True,
+    temperature = .2,
+    top_k = 50,
+    top_p = .95,
+    add_special_tokens = True 
+)
+
+print(outputs[0]['generated_text'][len(prompt):])
+```
+
+### Template
+
+```text
+# chat template
+<bos><start_of_turn>user\n다음 글을 요약해주세요:\n\n{data}<end_of_turn>\n<start_of_turn>model\n{label}
+```
+
 
 ### Direct Use
 
@@ -83,7 +128,9 @@ Use the code below to get started with the model.
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+- SFT
+- Quantization
+- DoRA
 
 #### Preprocessing [optional]
 
@@ -92,7 +139,12 @@ Use the code below to get started with the model.
 
 #### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+- per_device_train_batch_size: 2
+- gradient_accumulation_steps: 4
+- optimization: paged_adamw_8bit
+- lr: 2e-4
+- bf16: True
+- max_steps: 500
 
 #### Speeds, Sizes, Times [optional]
 
@@ -120,9 +172,15 @@ Use the code below to get started with the model.
 
 #### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+- Training Loss
 
-[More Information Needed]
+| Step | Training Loss |
+| --- | --- |
+|100 |1.528100 |
+|200 |1.409400 |
+|300 |1.372800 |
+|400 |1.325900 |
+|500 |1.341600 |
 
 ### Results
 
@@ -134,8 +192,6 @@ Use the code below to get started with the model.
 
 ## Model Examination [optional]
 
-<!-- Relevant interpretability work for the model goes here -->
-
 [More Information Needed]
 
 ## Environmental Impact