dvianna/LegalQA-bloomz-560m
Finetuning a small BLOOMZ model (bloomz-560m) on a small dataset and with limited resources.
This project helps legal professionals and those in tax-related roles in Brazil quickly find answers to specific questions within official tax documents. It takes raw PDF documents from the Brazilian Internal Revenue Service and transforms them into a structured dataset of questions and answers. The output is a specialized AI model capable of providing concise answers to queries based on this legal text.
No commits in the last 6 months.
Use this if you need an AI model specifically trained to answer questions about Brazilian tax regulations found in official government PDFs, and you want to leverage a pre-tuned model for this domain.
Not ideal if your questions are outside the domain of Brazilian tax law or if you require an AI model that can generate creative or conversational responses beyond direct question-answering.
Stars
18
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
May 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/dvianna/LegalQA-bloomz-560m"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
axolotl-ai-cloud/axolotl
Go ahead and axolotl questions
google/paxml
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for...
JosefAlbers/PVM
Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon
iamarunbrahma/finetuned-qlora-falcon7b-medical
Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset
h2oai/h2o-wizardlm
Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning