Instructions to use botbotrobotics/CabraMixtral-8x7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use botbotrobotics/CabraMixtral-8x7b with Transformers:

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

pipe = pipeline("text-generation", model="botbotrobotics/CabraMixtral-8x7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("botbotrobotics/CabraMixtral-8x7b")
model = AutoModelForCausalLM.from_pretrained("botbotrobotics/CabraMixtral-8x7b")
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

vLLM

How to use botbotrobotics/CabraMixtral-8x7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "botbotrobotics/CabraMixtral-8x7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "botbotrobotics/CabraMixtral-8x7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/botbotrobotics/CabraMixtral-8x7b

SGLang

How to use botbotrobotics/CabraMixtral-8x7b 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 "botbotrobotics/CabraMixtral-8x7b" \
    --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": "botbotrobotics/CabraMixtral-8x7b",
		"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 "botbotrobotics/CabraMixtral-8x7b" \
        --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": "botbotrobotics/CabraMixtral-8x7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use botbotrobotics/CabraMixtral-8x7b with Docker Model Runner:
```
docker model run hf.co/botbotrobotics/CabraMixtral-8x7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BotBot Cabra Mixtral 8x7b

Esse modelo é um finetune do Mixtral 8x7b com o dataset Cabra 30k. Esse modelo é optimizado para português. Ele apresenta melhoria em varios benchmarks brasileiros em comparação com o modelo base.

Conheça os nossos outros modelos: Cabra.

dataset: Cabra 30k

Dataset interno para finetuning. Vamos lançar em breve.

Quantização / GGUF

Colocamos diversas versões (GGUF) quantanizadas no branch "quantanization".

Exemplo

<s> [INST] who is Elon Musk? [/INST]Elon Musk é um empreendedor, inventor e capitalista americano. Ele é o fundador, CEO e CTO da SpaceX, CEO da Neuralink e fundador do The Boring Company. Musk também é o proprietário do Twitter.</s>

Uso

O modelo é destinado, por agora, a fins de pesquisa. As áreas e tarefas de pesquisa possíveis incluem:

Pesquisa sobre modelos gerativos.
Investigação e compreensão das limitações e viéses de modelos gerativos.

Proibido para uso comercial. Somente pesquisa.

Evals

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric	Value
Average	73.96
ENEM Challenge (No Images)	78.17
BLUEX (No Images)	64.12
OAB Exams	55.49
Assin2 RTE	90.95
Assin2 STS	77.63
FaQuAD NLI	78.93
HateBR Binary	78
PT Hate Speech Binary	69.54
tweetSentBR	72.83

Downloads last month: 9

Safetensors

Model size

47B params

Tensor type

BF16

Model tree for botbotrobotics/CabraMixtral-8x7b

Quantizations

2 models

Space using botbotrobotics/CabraMixtral-8x7b 1

Collection including botbotrobotics/CabraMixtral-8x7b

Models

Collection

Fine-tuned LLMs for the Portuguese language and Brazilian culture. • 10 items • Updated Jun 21, 2024 • 3

Evaluation results

accuracy on ENEM Challenge (No Images)
Open Portuguese LLM Leaderboard

78.170
accuracy on BLUEX (No Images)
Open Portuguese LLM Leaderboard

64.120
accuracy on OAB Exams
Open Portuguese LLM Leaderboard

55.490
f1-macro on Assin2 RTE
test set Open Portuguese LLM Leaderboard

90.950
pearson on Assin2 STS
test set Open Portuguese LLM Leaderboard

77.630
f1-macro on FaQuAD NLI
test set Open Portuguese LLM Leaderboard

78.930
f1-macro on HateBR Binary
test set Open Portuguese LLM Leaderboard

78.000
f1-macro on PT Hate Speech Binary
test set Open Portuguese LLM Leaderboard

69.540