Instructions to use rhaymison/Mistral-portuguese-luana-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rhaymison/Mistral-portuguese-luana-7b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rhaymison/Mistral-portuguese-luana-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rhaymison/Mistral-portuguese-luana-7b")
model = AutoModelForCausalLM.from_pretrained("rhaymison/Mistral-portuguese-luana-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rhaymison/Mistral-portuguese-luana-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rhaymison/Mistral-portuguese-luana-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhaymison/Mistral-portuguese-luana-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rhaymison/Mistral-portuguese-luana-7b

SGLang

How to use rhaymison/Mistral-portuguese-luana-7b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rhaymison/Mistral-portuguese-luana-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhaymison/Mistral-portuguese-luana-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rhaymison/Mistral-portuguese-luana-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhaymison/Mistral-portuguese-luana-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rhaymison/Mistral-portuguese-luana-7b with Docker Model Runner:
```
docker model run hf.co/rhaymison/Mistral-portuguese-luana-7b
```

Mistral-portuguese-luana-7b / README.md

rhaymison

Update README.md

fb9776a verified about 2 years ago

preview code

Raw

History Blame

2.65 kB

	---
	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 \|