---
language:
- pt
datasets:
- adalbertojunior/dolphin_pt_test
model-index:
- name: Llama-3-8B-Instruct-Portuguese-v0.2-fft
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: ENEM Challenge (No Images)
      type: eduagarcia/enem_challenge
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 59.69
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BLUEX (No Images)
      type: eduagarcia-temp/BLUEX_without_images
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 44.37
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: OAB Exams
      type: eduagarcia/oab_exams
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 39.09
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Assin2 RTE
      type: assin2
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: f1_macro
      value: 91.54
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Assin2 STS
      type: eduagarcia/portuguese_benchmark
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: pearson
      value: 77.89
      name: pearson
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: FaQuAD NLI
      type: ruanchaves/faquad-nli
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: f1_macro
      value: 68.51
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HateBR Binary
      type: ruanchaves/hatebr
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 82.27
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: PT Hate Speech Binary
      type: hate_speech_portuguese
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 63.01
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: tweetSentBR
      type: eduagarcia/tweetsentbr_fewshot
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 67.48
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft
      name: Open Portuguese LLM Leaderboard
---
## Como Utilizar
```
import transformers
import torch

model_id = "adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="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("<|im_end|>")
]

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):])
```
### Formato do prompt
```
<|im_start|>system
Você é um assistente útil com respostas curtas.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```


# Open Portuguese LLM Leaderboard Evaluation Results  

Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.2-fft) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)

|          Metric          |  Value  |
|--------------------------|---------|
|Average                   |**65.98**|
|ENEM Challenge (No Images)|    59.69|
|BLUEX (No Images)         |    44.37|
|OAB Exams                 |    39.09|
|Assin2 RTE                |    91.54|
|Assin2 STS                |    77.89|
|FaQuAD NLI                |    68.51|
|HateBR Binary             |    82.27|
|PT Hate Speech Binary     |    63.01|
|tweetSentBR               |    67.48|