You can deploy this model and start earning money today!

RichardErkhov/
adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-v0.3-gguf

Name: adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-v0.3-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3-8B-Dolphin-Portuguese-v0.3 - GGUF

Model creator: https://huggingface.co/adalbertojunior/
Original model: https://huggingface.co/adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3/

Name	Quant method	Size
Llama-3-8B-Dolphin-Portuguese-v0.3.Q2_K.gguf	Q2_K	2.96GB
Llama-3-8B-Dolphin-Portuguese-v0.3.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3-8B-Dolphin-Portuguese-v0.3.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3-8B-Dolphin-Portuguese-v0.3.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q3_K.gguf	Q3_K	3.74GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3-8B-Dolphin-Portuguese-v0.3.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q4_0.gguf	Q4_0	4.34GB
Llama-3-8B-Dolphin-Portuguese-v0.3.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q4_K.gguf	Q4_K	4.58GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q4_1.gguf	Q4_1	4.78GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q5_0.gguf	Q5_0	5.21GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q5_K.gguf	Q5_K	5.34GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q5_1.gguf	Q5_1	5.65GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q6_K.gguf	Q6_K	6.14GB
Llama-3-8B-Dolphin-Portuguese-v0.3.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers model-index:

name: Llama-3-8B-Dolphin-Portuguese-v0.3 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: 68.86 name: accuracy source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 57.86 name: accuracy source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 61.91 name: accuracy source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 93.05 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 76.48 name: pearson source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 76.78 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 83.25 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 68.85 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 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: 71.3 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3 name: Open Portuguese LLM Leaderboard datasets:
adalbertojunior/dolphin_portuguese_legal language:
pt

Model Card for Model ID

Model Card for Llama-3-8B-Dolphin-Portuguese-v0.3

Model Trained on a translated version of dolphin dataset.

Usage

python

import transformers
import torch

model_id = "adalbertojunior/Llama-3-8B-Dolphin-Portuguese-v0.3"

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	73.15
ENEM Challenge (No Images)	68.86
BLUEX (No Images)	57.86
OAB Exams	61.91
Assin2 RTE	93.05
Assin2 STS	76.48
FaQuAD NLI	76.78
HateBR Binary	83.25
PT Hate Speech Binary	68.85
tweetSentBR	71.30

RichardErkhov/adalbertojunior_-_Llama-3-8B-Dolphin-Portuguese-v0.3-gguf