README.md

Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


Llama-3-8B-Dolphin-Portuguese - GGUF
- Model creator: https://huggingface.co/adalbertojunior/
- Original model: https://huggingface.co/adalbertojunior/Llama-3-8B-Dolphin-Portuguese/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-3-8B-Dolphin-Portuguese.Q2_K.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q2_K.gguf) | Q2_K | 2.96GB |
| [Llama-3-8B-Dolphin-Portuguese.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [Llama-3-8B-Dolphin-Portuguese.IQ3_S.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [Llama-3-8B-Dolphin-Portuguese.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [Llama-3-8B-Dolphin-Portuguese.IQ3_M.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [Llama-3-8B-Dolphin-Portuguese.Q3_K.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q3_K.gguf) | Q3_K | 3.74GB |
| [Llama-3-8B-Dolphin-Portuguese.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [Llama-3-8B-Dolphin-Portuguese.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [Llama-3-8B-Dolphin-Portuguese.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [Llama-3-8B-Dolphin-Portuguese.Q4_0.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q4_0.gguf) | Q4_0 | 4.34GB |
| [Llama-3-8B-Dolphin-Portuguese.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [Llama-3-8B-Dolphin-Portuguese.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [Llama-3-8B-Dolphin-Portuguese.Q4_K.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q4_K.gguf) | Q4_K | 4.58GB |
| [Llama-3-8B-Dolphin-Portuguese.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [Llama-3-8B-Dolphin-Portuguese.Q4_1.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q4_1.gguf) | Q4_1 | 4.78GB |
| [Llama-3-8B-Dolphin-Portuguese.Q5_0.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q5_0.gguf) | Q5_0 | 5.21GB |
| [Llama-3-8B-Dolphin-Portuguese.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [Llama-3-8B-Dolphin-Portuguese.Q5_K.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q5_K.gguf) | Q5_K | 5.34GB |
| [Llama-3-8B-Dolphin-Portuguese.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [Llama-3-8B-Dolphin-Portuguese.Q5_1.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q5_1.gguf) | Q5_1 | 5.65GB |
| [Llama-3-8B-Dolphin-Portuguese.Q6_K.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q6_K.gguf) | Q6_K | 6.14GB |
| [Llama-3-8B-Dolphin-Portuguese.Q8_0.gguf](https://huggingface.co/RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-gguf/blob/main/Llama-3-8B-Dolphin-Portuguese.Q8_0.gguf) | Q8_0 | 7.95GB |




Original model description:

---
library_name: transformers
datasets:
- adalbertojunior/dolphin_pt_test
language:
- pt
model-index:
- name: Llama-3-8B-Dolphin-Portuguese
  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: 66.83
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 53.69
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 45.24
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 92.84
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 75.92
      name: pearson
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 79.67
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 88.04
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 58.34
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      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: 69.4
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese
      name: Open Portuguese LLM Leaderboard
---

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

Model Trained on a translated version of dolphin dataset.


## Usage
```python
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](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/adalbertojunior/Llama-3-8B-Dolphin-Portuguese) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_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|