🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
- adapter
- diffusion
- llm
- parameter-efficient-learning
107,098 visible repositories in the index
25–48 of 645 · Most stars
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Train transformer language models with reinforcement learning.
Machine Learning Engineering Open Book
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
State-of-the-Art Embeddings, Retrieval, and Reranking
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Ongoing research training transformer models at scale
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Datasets, Transforms and Models specific to Computer Vision
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
Air-gapped, privacy-focused, open-source NotebookLM alternative. AI agent that researches, transforms, and edits your documents. Join our Discord: https://discord.gg/ejRNvftDp9
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Nano vLLM
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
Image augmentation for machine learning experiments.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Clone of the Age of Empires II engine 🚀
A framework for few-shot evaluation of language models.
TranslatedTransfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-Transfer learning
Transform your favorite cities into beautiful, minimalist designs. MapToPoster lets you create and export visually striking map posters with code.