|
--- |
|
language: |
|
- es |
|
license: apache-2.0 |
|
datasets: |
|
- hackathon-somos-nlp-2023/Habilidades_Agente_v1 |
|
--- |
|
|
|
<div style="text-align:center;width:450px;height:450px;"> |
|
<img src="https://huggingface.co/hackathon-somos-nlp-2023/SalpiBloomZ_15949_input_512-1b7/resolve/main/salpi.png" alt="SAlsapaca logo""> |
|
</div> |
|
|
|
|
|
|
|
# SalpiBloomZ-1b7: Spanish + BloomZ + Alpaca + softskills + virtual agents (WIP) |
|
|
|
|
|
## Adapter Description |
|
This adapter was created with the [PEFT](https://github.com/huggingface/peft) library and allowed the base model [bigscience/bloomz-1b7](https://huggingface.co/bigscience/bloomz-1b7) to be fine-tuned on the [hackathon-somos-nlp-2023/Habilidades_Agente_v1](https://huggingface.co/datasets/hackathon-somos-nlp-2023/Habilidades_Agente_v1) 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/salsapaca-native" |
|
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(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) |
|
``` |
|
|
|
|
|
## Resources used |
|
Google Colab machine with the following specifications |
|
<div style="text-align:center;width:550px;height:550px;"> |
|
<img src="https://huggingface.co/hackathon-somos-nlp-2023/bertin-gpt-j-6B-es-finetuned-salpaca/resolve/main/resource.jpeg" alt="Resource logo"> |
|
</div> |
|
|
|
## Citation |
|
``` |
|
@misc {hackathon-somos-nlp-2023, |
|
author = { {Edison Bejarano, Leonardo Bolaños, Alberto Ceballos, Santiago Pineda, Nicolay Potes} }, |
|
title = { SAlsapaca }, |
|
year = 2023, |
|
url = { https://huggingface.co/hackathon-somos-nlp-2023/salsapaca-native } |
|
publisher = { Hugging Face } |
|
} |
|
``` |
