File size: 6,655 Bytes
dd755d8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Quickstart — Community Notes Reranker (PT-BR)\n",
"\n",
"Notebook mínimo de inferência. Baixa o modelo (base Qwen3-Reranker-0.6B + adapter LoRA), monta o template e devolve a probabilidade de utilidade para um par `(tweet, nota)`.\n",
"\n",
"- **Runtime sugerido:** GPU (T4 basta). CPU também funciona, mas ~5-10s por inferência.\n",
"- **Modos disponíveis:** *fold único* (rápido) e *ensemble dos 5 folds* (reproduz exatamente o número reportado no model card).\n"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"# Instala dependencias se necessario\n",
"import sys, subprocess, importlib\n",
"for mod, pkg in [(\"torch\",\"torch\"), (\"transformers\",\"transformers\"),\n",
" (\"peft\",\"peft\"), (\"huggingface_hub\",\"huggingface_hub\")]:\n",
" try: importlib.import_module(mod)\n",
" except Exception:\n",
" subprocess.run([sys.executable, \"-m\", \"pip\", \"install\", \"-q\", pkg], check=True)\n"
],
"outputs": [],
"execution_count": null
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Carrega base + um fold (modo rápido)"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"import json, torch\n",
"from transformers import AutoTokenizer, AutoModelForCausalLM\n",
"from peft import PeftModel\n",
"from huggingface_hub import snapshot_download\n",
"\n",
"REPO = \"histlearn/community-notes-reranker-ptbr\"\n",
"path = snapshot_download(REPO, allow_patterns=[\"manifesto.json\", \"adapter_fold_1/*\"])\n",
"m = json.load(open(f\"{path}/manifesto.json\"))\n",
"\n",
"tok = AutoTokenizer.from_pretrained(m[\"base_model\"], padding_side=\"left\")\n",
"dtype = torch.float16 if torch.cuda.is_available() else torch.float32\n",
"base = AutoModelForCausalLM.from_pretrained(m[\"base_model\"], torch_dtype=dtype)\n",
"model = PeftModel.from_pretrained(base, f\"{path}/adapter_fold_1\")\n",
"if torch.cuda.is_available(): model.cuda()\n",
"model.eval()\n",
"print(f\"Modelo pronto em: {model.device}\")\n"
],
"outputs": [],
"execution_count": null
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Função de inferência"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"def util_prob(tweet: str, nota: str) -> float:\n",
" \"\"\"Probabilidade de que a comunidade marcaria a nota como util.\n",
" Threshold otimo medido sob CV (Platt scaling) = 0.38.\"\"\"\n",
" text = (m[\"prompt_prefixo\"] + \"<Instruct>: \" + m[\"instrucao\"] +\n",
" \"\\n<Query>: \" + tweet + \"\\n<Document>: \" + nota + m[\"prompt_sufixo\"])\n",
" enc = tok(text, return_tensors=\"pt\", truncation=True, max_length=m[\"max_length\"]).to(model.device)\n",
" with torch.no_grad():\n",
" logits = model(**enc).logits[:, -1, :]\n",
" return float(torch.sigmoid(logits[:, m[\"id_yes\"]] - logits[:, m[\"id_no\"]]).item())\n"
],
"outputs": [],
"execution_count": null
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exemplo"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"tweet = (\"Lula anunciou que o salario minimo subira para R$ 5 mil em 2026.\")\n",
"nota = (\"E falso. Em 12/12/2024, o presidente Lula anunciou que o salario minimo \"\n",
" \"subiria de R$ 1.412 para R$ 1.518 a partir de janeiro de 2025, segundo a \"\n",
" \"Agencia Brasil (https://agenciabrasil.ebc.com.br). Nao ha qualquer \"\n",
" \"anuncio oficial de valor proximo a R$ 5 mil.\")\n",
"\n",
"p = util_prob(tweet, nota)\n",
"print(f\"P(util) = {p:.4f}\")\n",
"print(f\"Classificacao (threshold 0.38): {'UTIL' if p >= 0.38 else 'NAO-UTIL'}\")\n"
],
"outputs": [],
"execution_count": null
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Ensemble dos 5 folds (reproduz o número do model card)\n",
"\n",
"Para resultados estatisticamente comparáveis aos reportados (macro-F1 0.7920), use a média das probabilidades dos 5 adapters."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"from huggingface_hub import snapshot_download\n",
"path_full = snapshot_download(REPO, allow_patterns=[\"manifesto.json\", \"adapter_fold_*/*\"])\n",
"\n",
"def util_prob_ensemble(tweet: str, nota: str) -> float:\n",
" probs = []\n",
" for k in range(1, 6):\n",
" m_k = PeftModel.from_pretrained(base, f\"{path_full}/adapter_fold_{k}\")\n",
" m_k.eval()\n",
" text = (m[\"prompt_prefixo\"] + \"<Instruct>: \" + m[\"instrucao\"] +\n",
" \"\\n<Query>: \" + tweet + \"\\n<Document>: \" + nota + m[\"prompt_sufixo\"])\n",
" enc = tok(text, return_tensors=\"pt\", truncation=True, max_length=m[\"max_length\"]).to(m_k.device)\n",
" with torch.no_grad():\n",
" l = m_k(**enc).logits[:, -1, :]\n",
" probs.append(float(torch.sigmoid(l[:, m[\"id_yes\"]] - l[:, m[\"id_no\"]]).item()))\n",
" # Libera o adapter k antes de carregar o k+1\n",
" if hasattr(m_k, \"unload\"):\n",
" m_k.unload()\n",
" return sum(probs) / 5\n",
"\n",
"p_ens = util_prob_ensemble(tweet, nota)\n",
"print(f\"P(util) ensemble = {p_ens:.4f}\")\n"
],
"outputs": [],
"execution_count": null
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Próximos passos\n",
"\n",
"- Para documentação completa, métricas e contexto do projeto, ver o [model card](https://huggingface.co/histlearn/community-notes-reranker-ptbr).\n",
"- Para reproduzir o treino fold-a-fold ou regenerar os artefatos, ver o notebook `02_pipeline_experimento.ipynb` no [Space do projeto](https://huggingface.co/spaces/histlearn/communitynotesbr).\n",
"- Para o dataset bruto, ver [`histlearn/notas-comunidade-ptbr`](https://huggingface.co/datasets/histlearn/notas-comunidade-ptbr).\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
} |