Instructions to use adalbertojunior/Llama-3-8B-Dolphin-Portuguese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adalbertojunior/Llama-3-8B-Dolphin-Portuguese with Transformers:

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

pipe = pipeline("text-generation", model="adalbertojunior/Llama-3-8B-Dolphin-Portuguese")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adalbertojunior/Llama-3-8B-Dolphin-Portuguese")
model = AutoModelForCausalLM.from_pretrained("adalbertojunior/Llama-3-8B-Dolphin-Portuguese", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adalbertojunior/Llama-3-8B-Dolphin-Portuguese with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adalbertojunior/Llama-3-8B-Dolphin-Portuguese"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adalbertojunior/Llama-3-8B-Dolphin-Portuguese",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adalbertojunior/Llama-3-8B-Dolphin-Portuguese

SGLang

How to use adalbertojunior/Llama-3-8B-Dolphin-Portuguese 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 "adalbertojunior/Llama-3-8B-Dolphin-Portuguese" \
    --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": "adalbertojunior/Llama-3-8B-Dolphin-Portuguese",
		"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 "adalbertojunior/Llama-3-8B-Dolphin-Portuguese" \
        --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": "adalbertojunior/Llama-3-8B-Dolphin-Portuguese",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adalbertojunior/Llama-3-8B-Dolphin-Portuguese with Docker Model Runner:
```
docker model run hf.co/adalbertojunior/Llama-3-8B-Dolphin-Portuguese
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Llama-3-8B-Dolphin-Portuguese

Model Trained on a translated version of dolphin dataset.

Usage

import transformers
import torch

model_id = "adalbertojunior/Llama-3-8B-Dolphin-Portuguese"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "Você é um robô pirata que sempre responde como um pirata deveria!"},
    {"role": "user", "content": "Quem é você?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])

Open Portuguese LLM Leaderboard Evaluation Results

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

Metric	Value
Average	70.0
ENEM Challenge (No Images)	66.83
BLUEX (No Images)	53.69
OAB Exams	45.24
Assin2 RTE	92.84
Assin2 STS	75.92
FaQuAD NLI	79.67
HateBR Binary	88.04
PT Hate Speech Binary	58.34
tweetSentBR	69.40

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for adalbertojunior/Llama-3-8B-Dolphin-Portuguese

Quantizations

3 models

Dataset used to train adalbertojunior/Llama-3-8B-Dolphin-Portuguese

Spaces using adalbertojunior/Llama-3-8B-Dolphin-Portuguese 10

Evaluation results

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

66.830
accuracy on BLUEX (No Images)
Open Portuguese LLM Leaderboard

53.690
accuracy on OAB Exams
Open Portuguese LLM Leaderboard

45.240
f1-macro on Assin2 RTE
test set Open Portuguese LLM Leaderboard

92.840
pearson on Assin2 STS
test set Open Portuguese LLM Leaderboard

75.920
f1-macro on FaQuAD NLI
test set Open Portuguese LLM Leaderboard

79.670
f1-macro on HateBR Binary
test set Open Portuguese LLM Leaderboard

88.040
f1-macro on PT Hate Speech Binary
test set Open Portuguese LLM Leaderboard

58.340