metadata
language:
- pt
license: apache-2.0
library_name: transformers
tags:
- portuguese
- brasil
- gemma
- portugues
- instrucao
base_model: google/gemma-2b-it
datasets:
- rhaymison/superset
pipeline_tag: text-generation
model-index:
- name: gemma-portuguese-tom-cat-2b-it
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: 27.71
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 29.07
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 27.97
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 46.84
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 14.06
name: pearson
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 29.39
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 46.59
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 45.36
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
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: 18.86
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/gemma-portuguese-tom-cat-2b-it
name: Open Portuguese LLM Leaderboard
gemma-portuguese-tom-cat-2b-it
Model description
updated: 2024-04-10 20:06
The gemma-portuguese-tom-cat-2b-it model is a portuguese model trained with the superset dataset with 250,000 instructions. The model is mainly focused on text generation and instruction. The model was not trained on math and code tasks. The model is generalist with focus on understand portuguese inferences. With this fine tuning for portuguese, you can adjust the model for a specific field.
How to Use
from transformers import AutoTokenizer, pipeline
import torch
model = "rhaymison/gemma-portuguese-tom-cat-2b-it"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.bfloat16},
device="cuda",
)
messages = [
{
"role": "system",
"content": "Abaixo está uma instrução que descreve uma tarefa, juntamente com uma entrada que fornece mais contexto. Escreva uma resposta que complete adequadamente o pedido."
},
{"role": "user", "content": "Me conte sobre a ida do homem a Lua."},
]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(
prompt,
max_new_tokens=256,
do_sample=True,
temperature=0.2,
top_k=50,
top_p=0.95
)
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer2 = AutoTokenizer.from_pretrained("rhaymison/gemma-portuguese-tom-cat-2b-it")
model2 = AutoModelForCausalLM.from_pretrained("rhaymison/gemma-portuguese-tom-cat-2b-it", device_map={"":0})
tokenizer2.pad_token = tokenizer2.eos_token
tokenizer2.add_eos_token = True
tokenizer2.add_bos_token, tokenizer2.add_eos_token
tokenizer2.padding_side = "right"
def format_template( question:str):
system_prompt = "Abaixo está uma instrução que descreve uma tarefa, juntamente com uma entrada que fornece mais contexto. Escreva uma resposta que complete adequadamente o pedido."
text = f"""<bos>system
{system_prompt}<end_of_turn>
<start_of_turn>user
###instrução: {question} <end_of_turn>
<start_of_turn>model"""
return text
question = format_template("Me conte sobre a ida do homem a Lua")
device = "cuda:0"
inputs = tokenizer2(text, return_tensors="pt").to(device)
outputs = model2.generate(**inputs, max_new_tokens=256, do_sample=False)
output = tokenizer2.decode(outputs[0], skip_special_tokens=True, skip_prompt=True)
print(output.replace("model"," "))
Comments
Any idea, help or report will always be welcome.
email: [email protected]
Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard
| Metric | Value |
|---|---|
| Average | 31.76 |
| ENEM Challenge (No Images) | 27.71 |
| BLUEX (No Images) | 29.07 |
| OAB Exams | 27.97 |
| Assin2 RTE | 46.84 |
| Assin2 STS | 14.06 |
| FaQuAD NLI | 29.39 |
| HateBR Binary | 46.59 |
| PT Hate Speech Binary | 45.36 |
| tweetSentBR | 18.86 |