Downloads · 30 days
18
16% of all-time downloads
Polygl0t/portuguese-qwen3-4b-instruct-quality-judge
portuguese-qwen3-4b-instruct-quality-judge is a text generation model from Polygl0t. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Qwen3-4B Instruct Quality Judge is a Qwen3-4B based model that can be used for judging the quality of a user-assistant conversation, serving as a quality filter for instruction-following tasks. This model was trained…
Downloads · 30 days
18
16% of all-time downloads
All-time downloads
115
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8 GB · 100%
From the Hugging Face model README
Qwen3-4B Instruct Quality Judge is a Qwen3-4B based model that can be used for judging the quality of a user-assistant conversation, serving as a quality filter for instruction-following tasks. This model was trained on the Portuguese Instruct Quality Qwen Annotations dataset.
torch.optim.AdamW (cosine learning rate scheduler with 100 warmup steps)This repository has the source code used to train this model.
Here's an example of how to use Qwen3-4B Instruct Quality Judge for scoring a conversation in Portuguese:
from transformers import AutoTokenizer, AutoModelForCausalLM
import json_repair # Make sure to install this package if you haven't already
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained("Polygl0t/portuguese-qwen3-4b-instruct-quality-judge")
model = AutoModelForCausalLM.from_pretrained("Polygl0t/portuguese-qwen3-4b-instruct-quality-judge")
model.to(device)
good_messages = [
{
"role": "user",
"content": "Qual é a capital de Portugal?"
},
{
"role": "assistant",
"content": "A capital de Portugal é Lisboa."
}
]
bad_messages = [
{
"role": "user",
"content": "Qual é a capital de Portugal?"
},
{
"role": "assistant",
"content": "Minha cor favorita é azul."
}
]
for message in [good_messages, bad_messages]:
text = tokenizer.apply_chat_template(
message,
tokenize=False,
add_generation_prompt=True,
tools=None,
# The chat template can handle tools, but we don't use them in this case.
)
# This model was fine-tuned with sequences up to 6032 tokens long
inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
**inputs,
max_new_tokens=250,
)
output_ids = generated_ids[0][inputs["input_ids"].shape[1]:]
output = tokenizer.decode(output_ids, skip_special_tokens=True)
# `json_repair` allows us to safely parse the JSON output, turning it into a Python dictionary. But you can also manually parse the output if you prefer.
decoded_output = json_repair.loads(output)
print(
{
"input": message,
"int_score": decoded_output.get("score", None),
"justification": decoded_output.get("reason", None)
}
)
@misc{correa2026tucano2cool,
title={{Tucano 2 Cool: Better Open Source LLMs for Portuguese}},
author={Nicholas Kluge Corr{\^e}a and Aniket Sen and Shiza Fatimah and Sophia Falk and Lennard Landgraf and Julia Kastner and Lucie Flek},
year={2026},
eprint={2603.03543},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2603.03543},
}
Polyglot is a project funded by the Federal Ministry of Education and Research (BMBF) and the Ministry of Culture and Science of the State of North Rhine-Westphalia (MWK) as part of TRA Sustainable Futures (University of Bonn) and the Excellence Strategy of the federal and state governments.
We also gratefully acknowledge the granted access to the Marvin cluster hosted by University of Bonn along with the support provided by its High Performance Computing & Analytics Lab.
Qwen3-4B Instruct Quality Judge is licensed under the Apache License, Version 2.0. For more details, see the LICENSE file.