danielangelo1/llama-climate-change-stance-ptbr-lora

Climate Change Stance Classifier — Portuguese (LoRA · Llama 3.1 8B)

Fine-tuned LoRA adapter for stance detection in Brazilian Portuguese climate change discourse

---

Overview · Label Mapping · Quick Start · Dataset · Training · Limitations · Citation · Contact

---

Overview

This repository provides a LoRA (PEFT) adapter fine-tuned on top of meta-llama/Llama-3.1-8B for three-class stance classification in Portuguese climate change social media comments.

The model was developed as part of the research presented in:

A Decade of Climate Polarization on Brazilian YouTube using Language Models
Accepted at ASONAM 2026 — to be presented Aug 24–27, 2026, Rabat, Marrocos

Note: This repository contains only the LoRA adapter weights. The base model must be loaded separately from meta-llama/Llama-3.1-8B.

---

Label Mapping

Label	Class	Description
0	Denier	Explicitly expresses skepticism toward climate change; denies its occurrence; downplays its impacts; rejects anthropogenic responsibility; claims global warming is a "hoax," a "lie," a natural cycle, or a conspiracy; or articulates generalized denial of climate science.
1	Believer	Explicitly acknowledges climate change; agrees with the scientific consensus; expresses environmental concern; defends scientific evidence; or criticizes harmful practices such as deforestation or wildfires.
2	Inconclusive	Does not clearly belong to either of the above categories; contains ambiguous statements; expresses generic agreement or disagreement without clear stance; lacks sufficient information to infer position; or is irrelevant to the climate change debate.

---

Quick Start

Installation

pip install torch transformers peft accelerate

Inference

🔑 Access Token Required
The base model meta-llama/Llama-3.1-8B is a gated model. You must:

1. Request access at meta-llama/Llama-3.1-8B
2. Accept Meta's license agreement on Hugging Face
3. Generate a token at huggingface.co/settings/tokens and pass it via token= or run huggingface-cli login before loading the model

import warnings
import logging
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from peft import PeftModel

warnings.filterwarnings("ignore")
logging.getLogger("transformers").setLevel(logging.ERROR)
logging.getLogger("peft").setLevel(logging.ERROR)

base_model = "meta-llama/Llama-3.1-8B"
lora_model = "danielangelo1/llama-climate-change-stance-ptbr-lora"

# Access token required - request access at:
# https://huggingface.co/meta-llama/Llama-3.1-8B
HF_TOKEN = "your_token_here"

tokenizer = AutoTokenizer.from_pretrained(base_model, token=HF_TOKEN)
tokenizer.pad_token = tokenizer.eos_token

model = AutoModelForSequenceClassification.from_pretrained(
    base_model,
    num_labels=3,
    torch_dtype=torch.float16,
    device_map="auto",
    token=HF_TOKEN,
)
model.config.pad_token_id = tokenizer.pad_token_id
model = PeftModel.from_pretrained(model, lora_model, token=HF_TOKEN)
model.eval()

label_map = {0: "Denier", 1: "Believer", 2: "Inconclusive"}

text = "O aquecimento global é uma ameaça real e precisamos agir agora."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512).to(model.device)

with torch.no_grad():
    logits = model(**inputs).logits
    predicted_class = logits.argmax(dim=-1).item()

print(f"Predicted class: {predicted_class} -> {label_map[predicted_class]}")

---

Training Details

Hyperparameter	Value
Method	QLoRA (Quantized LoRA — PEFT)
Base Model	meta-llama/Llama-3.1-8B
Quantization	4-bit NF4 with bfloat16 computation
LoRA rank (r)	64
LoRA alpha	16
LoRA dropout	— (not applied)
Target modules	q_proj, k_proj, v_proj
Max sequence length	192 tokens
Epochs	Up to 20 (early stopping, patience = 3)
Batch size	128
Learning rate	2 × 10⁻⁴
Loss function	Weighted cross-entropy (inverse class frequency)
Validation metric	Macro F1
Cross-validation	Stratified 5-fold
Precision	Mixed (FP16)
Hardware	1× NVIDIA A40 48GB · Intel Xeon Gold 6442Y 2.6GHz · 512GB RAM

---

Citation

If you use this model or adapter in your research, please cite:

@inproceedings{morais2026climate,
  author    = {Daniel Morais and Diego H. M. Magalhaes and Gabriel H. Silva and Andrea Failla and Valeria de C. Santos and Helen C. S. C. Lima and Carlos H. G. Ferreira},
  title     = {A Decade of Climate Polarization on Brazilian YouTube using Language Models},
  booktitle = {Proceedings of the 18th International Conference on Advances in Social Networks Analysis and Mining-ASONAM 2026},
  year      = {2026},
  month     = {Aug},
  address   = {Rabat, Morocco},
  publisher = {Springer Nature},
  note      = {To appear}
}

---

Contact

Daniel Ângelo Rosa Morais
Universidade Federal de Ouro Preto (UFOP), Brazil
📧 daniel.morais@aluno.ufop.edu.br
📧 danielangelo1234@gmail.com

---