metadata
language:
- pt
- en
library_name: adapter-transformers
datasets:
- dominguesm/alpaca-data-pt-br
pipeline_tag: text-generation
thumbnail: >-
https://blog.cobasi.com.br/wp-content/uploads/2022/08/AdobeStock_461738919.webp
model-index:
- name: Caramelo_7B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: ENEM Challenge (No Images)
type: eduagarcia/enem_challenge
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 19.8
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BLUEX (No Images)
type: eduagarcia-temp/BLUEX_without_images
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 24.48
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: OAB Exams
type: eduagarcia/oab_exams
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 25.28
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 RTE
type: assin2
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 54.27
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 STS
type: eduagarcia/portuguese_benchmark
split: test
args:
num_few_shot: 15
metrics:
- type: pearson
value: 7.47
name: pearson
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: FaQuAD NLI
type: ruanchaves/faquad-nli
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 43.97
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HateBR Binary
type: ruanchaves/hatebr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 33.65
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: PT Hate Speech Binary
type: hate_speech_portuguese
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 41.23
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: tweetSentBR
type: eduagarcia-temp/tweetsentbr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 35.37
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
name: Open Portuguese LLM Leaderboard
CARAMELO
Adapter Description
This adapter was created with the PEFT library and allowed the base model Falcon-7b to be fine-tuned on the https://huggingface.co/datasets/dominguesm/alpaca-data-pt-br by using the method QLoRA.
Model description
Intended uses & limitations
TBA
Training and evaluation data
TBA
Training results
How to use
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, GenerationConfig
peft_model_id = "Bruno/Caramelo_7B"
config = PeftConfig.from_pretrained(peft_model_id)
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.float16,
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path,
return_dict=True,
quantization_config=bnb_config,
trust_remote_code=True,
device_map={"": 0})
prompt_input = "Abaixo está uma declaração que descreve uma tarefa, juntamente com uma entrada que fornece mais contexto. Escreva uma resposta que conclua corretamente a solicitação.\n\n ### Instrução:\n{instruction}\n\n### Entrada:\n{input}\n\n### Resposta:\n"
prompt_no_input = "Abaixo está uma instrução que descreve uma tarefa. Escreva uma resposta que conclua corretamente a solicitação.\n\n### Instrução:\n{instruction}\n\n### Resposta:\n"
def create_prompt(instruction, input=None):
if input:
return prompt_input.format(instruction=instruction, input=input)
else:
return prompt_no_input.format(instruction=instruction)
def generate(
instruction,
input=None,
max_new_tokens=128,
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=4,
repetition_penalty=1.5,
max_length=512
):
prompt = create_prompt(instruction, input)
inputs = tokenizer.encode_plus(prompt, return_tensors="pt", truncation=True, max_length=max_length, padding="longest")
input_ids = inputs["input_ids"].to("cuda")
attention_mask = inputs["attention_mask"].to("cuda")
generation_output = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
max_length=max_length,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
temperature=temperature,
top_p=top_p,
top_k=top_k,
num_beams=num_beams,
repetition_penalty=repetition_penalty,
length_penalty=0.8,
early_stopping=True,
output_scores=True,
return_dict_in_generate=True
)
output = tokenizer.decode(generation_output.sequences[0], skip_special_tokens=True)
return output.split("### Resposta:")[1]
instruction = "como faço um bolo de cenoura?"
print(Instrução:", instruction)
print("Resposta:", generate(instruction))
### Saída
Instrução: como faço um bolo de cenoura?
Resposta:
1. Pegue uma cenoura e corte-a em pedaços pequenos.
2. Coloque os pedaços de cenoura em uma panela e cozinhe por 10 minutos.
3. Retire a cenoura da panela e deixe-a esfriar.
4. Coloque a cenoura em uma bolsa de plástico e congele.
5. Quando precisar, coloque a cenoura congelada na máquina de bolo.
### Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
# [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/Bruno/Caramelo_7B)
| Metric | Value |
|--------------------------|---------|
|Average |**31.73**|
|ENEM Challenge (No Images)| 19.80|
|BLUEX (No Images) | 24.48|
|OAB Exams | 25.28|
|Assin2 RTE | 54.27|
|Assin2 STS | 7.47|
|FaQuAD NLI | 43.97|
|HateBR Binary | 33.65|
|PT Hate Speech Binary | 41.23|
|tweetSentBR | 35.37|