Update README.md

README.md

@@ -27,6 +27,11 @@ It achieves the following results on the evaluation set:
 
 ## Sample Code
 
+### Requirements
+```python
+!pip install accelerate transformers einops datasets peft bitsandbytes
+```
+
 ### 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.
@@ -57,16 +62,16 @@ model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, tru
 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)
+#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)
 ```
 
 ```python
-#Put from dataset
-inputs = tokenizer(f'''{formatted_dataset['text'][120]}''', return_tensors="pt", return_attention_mask=False)
+#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)