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 estรก uma instruรงรฃo 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 estรก uma instruรงรฃo 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
###instruรงรฃo: {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 ๐ 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 |
- Downloads last month
- 26
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for rhaymison/gemma-portuguese-tom-cat-2b-it
Dataset used to train rhaymison/gemma-portuguese-tom-cat-2b-it
Space using rhaymison/gemma-portuguese-tom-cat-2b-it 1
Evaluation results
- accuracy on ENEM Challenge (No Images)Open Portuguese LLM Leaderboard27.710
- accuracy on BLUEX (No Images)Open Portuguese LLM Leaderboard29.070
- accuracy on OAB ExamsOpen Portuguese LLM Leaderboard27.970
- f1-macro on Assin2 RTEtest set Open Portuguese LLM Leaderboard46.840
- pearson on Assin2 STStest set Open Portuguese LLM Leaderboard14.060
- f1-macro on FaQuAD NLItest set Open Portuguese LLM Leaderboard29.390
- f1-macro on HateBR Binarytest set Open Portuguese LLM Leaderboard46.590
- f1-macro on PT Hate Speech Binarytest set Open Portuguese LLM Leaderboard45.360
- f1-macro on tweetSentBRtest set Open Portuguese LLM Leaderboard18.860