phi-3-portuguese-tom-cat-4k-instruct-GGUF
Quantized GGUF model files for phi-3-portuguese-tom-cat-4k-instruct from rhaymison
Original Model Card:
Phi-3-portuguese-tom-cat-4k-instruct
This model was trained with a superset of 300,000 instructions in Portuguese. The model comes to help fill the gap in models in Portuguese. Tuned from the microsoft/Phi-3-mini-4k.
How to use
FULL MODEL : A100
HALF MODEL: L4
8bit or 4bit : T4 or V100
You can use the model in its normal form up to 4-bit quantization. Below we will use both approaches. Remember that verbs are important in your prompt. Tell your model how to act or behave so that you can guide them along the path of their response. Important points like these help models (even smaller models like 4b) to perform much better.
!pip install -q -U transformers
!pip install -q -U accelerate
!pip install -q -U bitsandbytes
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model = AutoModelForCausalLM.from_pretrained("rhaymison/phi-3-portuguese-tom-cat-4k-instruct", device_map= {"": 0})
tokenizer = AutoTokenizer.from_pretrained("rhaymison/phi-3-portuguese-tom-cat-4k-instruct")
model.eval()
You can use with Pipeline.
from transformers import pipeline
pipe = pipeline("text-generation",
model=model,
tokenizer=tokenizer,
do_sample=True,
max_new_tokens=512,
num_beams=2,
temperature=0.3,
top_k=50,
top_p=0.95,
early_stopping=True,
pad_token_id=tokenizer.eos_token_id,
)
def format_template(question:str):
system_prompt = "Abaixo está uma instrução que descreve uma tarefa, juntamente com uma entrada que fornece mais contexto. Escreva uma resposta que complete adequadamente o pedido."
return f"""<s><|system|>
{ system_prompt }
<|user|>
{ question }
<|assistant|>
"""
question = format_template("E possivel ir de Carro dos Estados unidos ate o japão")
pipe(question)
If you are having a memory problem such as "CUDA Out of memory", you should use 4-bit or 8-bit quantization. For the complete model in colab you will need the A100. If you want to use 4bits or 8bits, T4 or L4 will already solve the problem.
4bits example
from transformers import BitsAndBytesConfig
import torch
nb_4bit_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True
)
model = AutoModelForCausalLM.from_pretrained(
base_model,
quantization_config=bnb_config,
device_map={"": 0}
)
Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard
Metric | Value |
---|---|
Average | 64.57 |
ENEM Challenge (No Images) | 61.58 |
BLUEX (No Images) | 50.63 |
OAB Exams | 43.69 |
Assin2 RTE | 91.54 |
Assin2 STS | 75.27 |
FaQuAD NLI | 47.46 |
HateBR Binary | 83.01 |
PT Hate Speech Binary | 70.19 |
tweetSentBR | 57.78 |
Comments
Any idea, help or report will always be welcome.
email: rhaymisoncristian@gmail.com
- Downloads last month
- 61
Model tree for afrideva/phi-3-portuguese-tom-cat-4k-instruct-GGUF
Base model
microsoft/Phi-3-mini-4k-instructDataset used to train afrideva/phi-3-portuguese-tom-cat-4k-instruct-GGUF
Evaluation results
- accuracy on ENEM Challenge (No Images)Open Portuguese LLM Leaderboard61.580
- accuracy on BLUEX (No Images)Open Portuguese LLM Leaderboard50.630
- accuracy on OAB ExamsOpen Portuguese LLM Leaderboard43.690
- f1-macro on Assin2 RTEtest set Open Portuguese LLM Leaderboard91.540
- pearson on Assin2 STStest set Open Portuguese LLM Leaderboard75.270
- f1-macro on FaQuAD NLItest set Open Portuguese LLM Leaderboard47.460
- f1-macro on HateBR Binarytest set Open Portuguese LLM Leaderboard83.010
- f1-macro on PT Hate Speech Binarytest set Open Portuguese LLM Leaderboard70.190
- f1-macro on tweetSentBRtest set Open Portuguese LLM Leaderboard57.780