---
library_name: transformers
tags:
- Misral
- Portuguese
- 7b
license: apache-2.0
datasets:
- pablo-moreira/gpt4all-j-prompt-generations-pt
- rhaymison/superset
language:
- pt
pipeline_tag: text-generation
---

# Mistral-portuguese-luana-7b

This model was trained with a superset of 200,000 instructions in Portuguese. 
The model comes to help fill the gap in models in Portuguese. Tuned from the Mistral 7b in Portuguese, the model was adjusted mainly for instructional tasks.


# How to use

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 7b) 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/Mistral-portuguese-luana-7b", device_map= {"": 0})
tokenizer = AutoTokenizer.from_pretrained("rhaymison/Mistral-portuguese-luana-7b")
model.eval()

```

You can use with Pipeline but in this example i will use such as Streaming
```python

inputs = tokenizer([f"""<s>[INST] Abaixo está uma instrução que descreve uma tarefa, juntamente com uma entrada que fornece mais contexto.
Escreva uma resposta que complete adequadamente o pedido.
### instrução: aja como um professor de matemática e me explique porque 2 + 2 = 4.
[/INST]"""], return_tensors="pt")

streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=200)

```

# 4bits

```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}
)

```


## Benchmark test

benchmark: portuguese-benchmark-datasets/BLUEX
| Metric           | Valor      |
|-------------------|------------|
| Hits           | 485        |
| Erros             | 600        |
| Total Questions | 1.085      |
| Percentage | 44.70%  |

benchmark: rhaymison/benchmark-summarization

| Metric           | Valor      |
|-------------------|------------|
| ROUGE-1           | 0.62       |
| ROUGE-2           | 0.49       |
| ROUGE-L           | 0.58       |