README.md

---
language:
- pt
license: apache-2.0
library_name: transformers
tags:
- portugues
- portuguese
- QA
- instruct
- phi
base_model: microsoft/Phi-3-mini-4k-instruct
datasets:
- rhaymison/superset
pipeline_tag: text-generation
---

# Llama3-portuguese-luana-8b-instruct

<p align="center">
 <img src="https://raw.githubusercontent.com/rhaymisonbetini/huggphotos/main/tom-cat.webp" width="50%" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
</p>


This model was trained with a superset of 300,000 chat 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 8b) to perform much better.

```python
!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-instructt", device_map= {"": 0})
tokenizer = AutoTokenizer.from_pretrained("rhaymison/phi-3-portuguese-tom-cat-4k-instruct")
model.eval()

```

You can use with Pipeline.
```python

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

```python
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}
)

```


### Comments

Any idea, help or report will always be welcome.

email: [email protected]

 <div style="display:flex; flex-direction:row; justify-content:left">
 <a href="https://www.linkedin.com/in/heleno-betini-2b3016175/" target="_blank">
 <img src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white">
 </a>
 <a href="https://github.com/rhaymisonbetini" target="_blank">
 <img src="https://img.shields.io/badge/GitHub-100000?style=for-the-badge&logo=github&logoColor=white">
 </a>