---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: titletor-phi_1-5
  results: []
datasets:
- zelalt/scientific-papers-3.5-withprompt
---

<div align="center">

# Titletor

</div>


<div align="center">
  <img src="./titletor.png" width="300"/>
</div>

This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on [zelalt/scientific-papers-3.5-withprompt](https://huggingface.co/datasets/zelalt/scientific-papers-3.5-withprompt) dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1587

## Model description

## 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.

```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

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 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 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)
```

After running it for the first time and loading the model and tokenizer, you can only run generating part to avoid RAM crash.

### Output
Input:
```
What is the title of this paper? Bursting Dynamics of the 3D Euler Equations\nin Cylindrical Domains\nFrançois Golse ∗ †\nEcole Polytechnique, CMLS\n91128 Palaiseau Cedex, France\nAlex Mahalov ‡and Basil Nicolaenko §\n\nAnswer:
```

## Output from LLM:

```
What is the title of this paper? Bursting Dynamics of the 3D Euler Equations
in Cylindrical Domains
François Golse ∗ †
Ecole Polytechnique, CMLS
91128 Palaiseau Cedex, France
Alex Mahalov ‡and Basil Nicolaenko §

Answer:  Bursting Dynamics of the 3D Euler Equations in Cylindrical Domains<|endoftext|>
```

## Training and evaluation data
Train and validation dataset:
[zelalt/scientific-papers-3.5-withprompt](https://huggingface.co/datasets/zelalt/scientific-papers-3.5-withprompt)


## Training procedure

### Training hyperparameters

- total_train_batch_size: 8
- lr_scheduler_type: cosine

### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0