MilaNLProc/simple-generation
A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.
This tool helps researchers and data scientists efficiently generate text and image captions using existing large language models and vision-language models. You provide a prompt or an image, and it outputs generated text. It's designed for individuals working on AI experiments or internal projects that require quick model inference without complex setup.
No commits in the last 6 months.
Use this if you need a straightforward way to run text generation or image captioning on your personal machine or a single server with multiple GPUs, without writing extensive code.
Not ideal if you need a production-ready inference engine for high-volume, mission-critical applications or if you require fine-grained control over every model loading and generation parameter.
Stars
28
Forks
3
Language
Python
License
—
Category
Last pushed
Sep 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/MilaNLProc/simple-generation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
batzner/tensorlm
Wrapper library for text generation / language models at character and word level with RNNs in TensorFlow
EagleW/PaperRobot
Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
Cyrilvallez/TextWiz
An even simpler way to generate text with LLMs.
microsoft/CodeMixed-Text-Generator
This tool helps automatic generation of grammatically valid synthetic Code-mixed data by...
yingpengma/Awesome-Story-Generation
This repository collects an extensive list of awesome papers about Story Generation /...