NVIDIA/logits-processor-zoo
A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.
This collection helps developers customize how large language models (LLMs) generate text, going beyond basic grammar. It takes an existing LLM and instructions for specific output styles, then produces text that adheres more closely to those instructions, such as citing from the prompt or answering multiple-choice questions correctly. It's for developers building applications where precise LLM control is crucial, like for chatbots or automated content generation.
384 stars. No commits in the last 6 months.
Use this if you are a developer building an LLM application and need fine-grained control over the model's output beyond standard prompting, for tasks like ensuring specific phrasing, controlling response length, or preventing certain types of output.
Not ideal if you are an end-user simply interacting with an LLM and do not have programming expertise to implement custom generation logic.
Stars
384
Forks
24
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NVIDIA/logits-processor-zoo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AI-Hypercomputer/maxtext
A simple, performant and scalable Jax LLM!
rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
mindspore-lab/mindnlp
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless...
mosaicml/llm-foundry
LLM training code for Databricks foundation models
rickiepark/llm-from-scratch
<밑바닥부터 만들면서 공부하는 LLM>(길벗, 2025)의 코드 저장소