Update README.md

README.md

@@ -25,15 +25,48 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-### Sample Code
+## Sample Code
 
+### Test Dataset
+If you prefer, you can use test dataset from [zelalt/scientific-papers](https://huggingface.co/datasets/zelalt/scientific-papers)
+or [zelalt/arxiv-papers](https://huggingface.co/datasets/zelalt/arxiv-papers) or read your pdf as text with PyPDF2.PdfReader then give this text to LLM with adding "What is the title of this paper?" prompt.
+
+```python
+from datasets import load_dataset
+
+test_dataset = load_dataset("zelalt/scientific-papers", split='train')
+test_dataset = test_dataset.rename_column('full_text', 'text')
+
+def formatting_prompts_func(example):
+    text = f"What is the title of this paper? {example['text'][:180]}\n\nAnswer: "
+    return {'text': text}
+
+formatted_dataset = test_dataset.map(formatting_prompts_func)
+```
+
+### Inference
 ```python
+
 import torch
+from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("zelalt/titletor-phi_1-5", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("zelalt/titletor-phi_1-5", trust_remote_code=True)
-inputs = tokenizer(f'''What is the title of this paper? ....[your pdf as text]\n\nAnswer: ''', return_tensors="pt", return_attention_mask=False)
+peft_model_id = "zelalt/titletor-phi_1-5"
+config = PeftConfig.from_pretrained(peft_model_id)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path,trust_remote_code=True)
+model = PeftModel.from_pretrained(model, peft_model_id)
+
+#Put as string
+inputs = tokenizer(f'''What is the title of this paper? ...[your pdf as text]..\n\nAnswer: ''', return_tensors="pt", return_attention_mask=False)
+outputs = model.generate(**inputs,max_new_tokens=50, pad_token_id = tokenizer.eos_token_id, eos_token_id = tokenizer.eos_token_id)
+text = tokenizer.batch_decode(outputs)[0]
+print(text)
+```
+
+```python
+#Put from dataset
+inputs = tokenizer(f'''{formatted_dataset['text'][120]}''', return_tensors="pt", return_attention_mask=False)
 outputs = model.generate(**inputs,max_new_tokens=50, pad_token_id = tokenizer.eos_token_id, eos_token_id = tokenizer.eos_token_id)
 text = tokenizer.batch_decode(outputs)[0]
 print(text)