---
license: apache-2.0
datasets:
- mlsum
- squad_es
language:
- es
library_name: adapter-transformers
pipeline_tag: text2text-generation
---
# Model Card for opt-6.7b-lora-sag-t12000-v1200-v1

## Adapter Description

This adapter was created as part of the SomosNLP Hackathon 2023 with the [PEFT](https://github.com/huggingface/peft) library and allowed the base model [facebook/opt-6.7b](https://huggingface.co/facebook/opt-6.7b) to be fine-tuned on the [SQUAD_ES](https://huggingface.co/datasets/squad_es) (v1.1.0) and [MLSUM](https://huggingface.co/datasets/mlsum) by using the method *LoRA*.

- **Developed by:**
  - 🇵🇪 Enrique Ubaldo
  - 🇵🇪 Fernando Alva-Manchego
  - 🇵🇪 @Levi111
  - 🇲🇽 @IvanHU
  - 🇨🇺 [Alberto Carmona Barthelemy](https://huggingface.co/milyiyo)
- **Model type:** Text2Text Generation
- **Language(s) (NLP):** Spanish
- **License:** apache-2.0


## 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. -->

This model is designed for use in Spanish language instruction, specifically for tasks such as generating summaries, creating questions, and generating answers based on a given context and question.

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

Please note that this model inherits biases from its original base model. You can review these biases by visiting the following [link](https://huggingface.co/facebook/opt-6.7b#limitations-and-bias).

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model.

```py
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig

peft_model_id = "hackathon-somos-nlp-2023/opt-6.7b-lora-sag-t14000-v1400-v1"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto')
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id)

model.config.use_cache = True

generation_config = GenerationConfig(temperature=.8,
                                     top_p=0.75,
                                     top_k=40)

def gen_summary(text):
  input_text = f'<s>Instruction: Elabora un resume del siguiente texto.\nInput: {text}\nOutput: '
  batch = tokenizer(input_text, return_tensors='pt')
  with torch.cuda.amp.autocast():
    output_tokens = model.generate(**batch, 
                                   max_new_tokens=256, 
                                   generation_config=generation_config)
  output = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
  return output

def gen_question(text):
  input_text = f'<s>Instruction: Dado el siguiente texto quiero que generes una pregunta cuya respuesta se encuentre en él.\nInput: {text}\nOutput: '
  batch = tokenizer(input_text, return_tensors='pt')
  with torch.cuda.amp.autocast():
    output_tokens = model.generate(**batch, 
                                   max_new_tokens=256, 
                                   generation_config=generation_config)
  output = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
  return output

def gen_qna(context, question):
  input_text = f"""<s>Instruction: Te voy a proporcionar un texto del cual deseo que me respondas una pregunta. 
    El texto es el siguiente: `{context}`\nInput: {question}\nOutput: """
  batch = tokenizer(input_text, return_tensors='pt')
  with torch.cuda.amp.autocast():
    output_tokens = model.generate(**batch, 
                                   max_new_tokens=256, 
                                   generation_config=generation_config)
  output = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
  return output
```

## Training Details

### Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

- [SQUAD_ES](https://huggingface.co/datasets/squad_es) (Subset: v1.1.0)
- [MLSUM](https://huggingface.co/datasets/mlsum) (Subset: es)

### Training Procedure 

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

We selected 4000 examples for each of the three tasks in the training dataset, and 400 examples for each task in the validation dataset. 
This resulted in a total of 12000 examples for training and 1200 examples for validation.

The Colab used for training is [here](https://colab.research.google.com/drive/1mwLUNgsSLrRbHUiXJuaU_6EQaYrYg10A?usp=sharing).

#### Training Hyperparameters

- **Training regime:** fp16 <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
- **Steps:**: 1240
- **Learning rate:**: 2e-4
- **Training loss:**: 1.013
- **Validation loss:**: 1.53
- **Training duration:**: 7.5 hours

WandB link: [here](https://wandb.ai/milyiyo/huggingface/reports/eval-loss-train-loss-23-04-08-19-14-44---Vmlldzo0MDEwMzQ5?accessToken=o5f3pldc7np25ch8123rcjz4195vrcc9nl31r26i130jhhpvuabie3ezrw6dcs6r)



<!--## Environmental Impact -->

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

<!--Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** T4 16GB (Free Colab)
- **Hours used:** 7.5 hour
- **Cloud Provider:** Google Cloud Platform
- **Compute Region:** us-central1?
- **Carbon Emitted:** Total emissions are estimated to be 0.04 kgCO$_2$eq of which 100 percents were directly offset by the cloud provider.
-->