{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "BaruqueRodrigues/llm-legislativo",
 "name": "llm-legislativo",
 "owner": "BaruqueRodrigues",
 "slug": "baruquerodrigues-llm-legislativo",
 "github": "https://github.com/BaruqueRodrigues/llm-legislativo",
 "what": "A Brazilian legislative text corpus from the Câmara dos Deputados and Senado Federal, plus a causal Transformer language model trained from scratch in pure PyTorch.",
 "why": "",
 "language": "Python",
 "requirements": [
  "A Python environment (the README install section is cut off in the source, so exact setup steps are unconfirmed)",
  "Internet access to Hugging Face Hub and GitHub",
  "Enough disk space for the Parquet release if you download corpus files (the raw TAR archives total over 360 GiB)",
  "Basic familiarity with PyTorch and Hugging Face datasets for the model and corpus steps"
 ],
 "audience_note": "Researchers, legal-data engineers, and ML students who need open Brazilian legislative text or a readable from-scratch GPT-style model to study or reuse.",
 "risk": "dual-use",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/baruquerodrigues-llm-legislativo/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "baruquerodrigues-llm-legislativo--study-from-scratch-transformer-code",
   "title": "Study a from-scratch causal Transformer in PyTorch",
   "best": true,
   "url": "https://dedupedai.com/use-cases/baruquerodrigues-llm-legislativo/study-from-scratch-transformer-code/",
   "json": "https://dedupedai.com/use-cases/u/baruquerodrigues-llm-legislativo/study-from-scratch-transformer-code.json"
  },
  {
   "id": "baruquerodrigues-llm-legislativo--load-and-generate-with-legislative-model",
   "title": "Load the Brazilian legislative model and generate text",
   "best": false,
   "url": "https://dedupedai.com/use-cases/baruquerodrigues-llm-legislativo/load-and-generate-with-legislative-model/",
   "json": "https://dedupedai.com/use-cases/u/baruquerodrigues-llm-legislativo/load-and-generate-with-legislative-model.json"
  },
  {
   "id": "baruquerodrigues-llm-legislativo--reuse-curated-legislative-corpus",
   "title": "Build a Portuguese legislative text dataset",
   "best": false,
   "url": "https://dedupedai.com/use-cases/baruquerodrigues-llm-legislativo/reuse-curated-legislative-corpus/",
   "json": "https://dedupedai.com/use-cases/u/baruquerodrigues-llm-legislativo/reuse-curated-legislative-corpus.json"
  },
  {
   "id": "baruquerodrigues-llm-legislativo--reproduce-byte-nll-evaluation",
   "title": "Reproduce the byte_nll_v1 evaluation numbers",
   "best": false,
   "url": "https://dedupedai.com/use-cases/baruquerodrigues-llm-legislativo/reproduce-byte-nll-evaluation/",
   "json": "https://dedupedai.com/use-cases/u/baruquerodrigues-llm-legislativo/reproduce-byte-nll-evaluation.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}