Finetuning-Suite
Finetune any model on HF in less than 30 seconds
Browse the latest quality-filtered tools added to YunoDB from verified public project data.
22806 tools
Finetune any model on HF in less than 30 seconds
This framework works as a form of user/machine calibration, with a focus on user-context and user-intent, deconstructing your ideas logically from A to B to Z.
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning
NEO Series: Native Vision-Language Models from First Principles
Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.
[NeurIPS 2025] LLM-driven framework to adaptively evolve Gaussian process kernels
The official code repository supporting the book, Grokking Artificial Intelligence Algorithms
Generates a quiz from a URL. You can play the quiz, or let the LLM play it.
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
ACL 2024 | LooGLE: Long Context Evaluation for Long-Context Language Models
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
FusionBench: A Comprehensive Benchmark/Toolkit of Deep Model Fusion
A Python toolbox for conformal prediction research on deep learning models, using PyTorch.
Benchmarking data agents for verifiable analytics over heterogeneous workspaces.
BioDSA: Framework for Vibe Prototyping of AI Agents for Biomedicine
Transformer-powered hashtag segmentation with beam search, RRF ensembles, and agent-ready MCP workflows. A scalable alternative to heuristic splitters and massi
ICLR 2026 code for Echoes as Anchors: why large reasoning models restate the question in long chain-of-thought. Echo-Distilled SFT, training-free Echoic Prompti
[ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs"
Official implementation of Meta Prompting for AI Systems (https://arxiv.org/abs/2311.11482)
A powerful and customizable ChatGPT-like interface, built for developers.
hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM, and VRAM into a sin
Companion code for FanOutQA: Multi-Hop, Multi-Document Question Answering for Large Language Models (ACL 2024)
A collection of resources on applications of multi-modal learning in medical imaging.