---
datasets:
- bertin-project/alpaca-spanish
language:
- es
license: apache-2.0
---

<div style="text-align:center;width:350px;height:350px;">
    <img src="https://huggingface.co/hackathon-somos-nlp-2023/bertin-gpt-j-6B-es-finetuned-salpaca/resolve/main/Alpaca.png" alt="SAlpaca logo"">
</div>



# SAlpaca: Spanish + Alpaca


## Adapter Description
This adapter was created with the [PEFT](https://github.com/huggingface/peft) library and allowed the base model *bertin-project/bertin-gpt-j-6B* to be fine-tuned on the *Spanish Alpaca Dataset* by using the method *LoRA*.


## How to use
```py
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

peft_model_id = "hackathon-somos-nlp-2023/bertin-gpt-j-6B-es-finetuned-salpaca"
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)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)

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

def gen_conversation(text):
  text = "<SC>instruction: " + text + "\n "
  batch = tokenizer(text, return_tensors='pt')
  with torch.cuda.amp.autocast():
    output_tokens = model.generate(**batch, max_new_tokens=256, eos_token_id=50258, early_stopping = True, temperature=.9)

  print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=False))

text = "hola"

gen_conversation(text)
```

## Citation
```
@misc {hackathon-somos-nlp-2023,
	author       = { {Edison Bejarano, Leonardo Bolaños, Santiago Pineda, Nicolay Potes, Daniel Terraza} },
	title        = { SAlpaca },
	year         = 2023,
	url          = { https://huggingface.co/hackathon-somos-nlp-2023/bertin-gpt-j-6B-es-finetuned-salpaca }
	publisher    = { Hugging Face }
}
```