Stars
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.
Wiseflow is an agile information mining tool that extracts concise messages from various sources such as websites, WeChat official accounts, social platforms, etc. It automatically categorizes and …
CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simpl…
A ComfyUI workflows and models management extension to organize and manage all your workflows, models in one place. Seamlessly switch between workflows, as well as import, export workflows, reuse s…
A plugin for multilingual translation of ComfyUI,This plugin implements translation of resident menu bar/search bar/right-click context menu/node, etc
ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, th…
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
LLMs interview notes and answers:该仓库主要记录大模型(LLMs)算法工程师相关的面试题和参考答案
Instruct-tune LLaMA on consumer hardware
Awesome-LLM: a curated list of Large Language Model
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
bdashore3 / flash-attention
Forked from Dao-AILab/flash-attentionFast and memory-efficient exact attention
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
MinusX is an AI Data Scientist for Analytics Apps you already use and love. Currently it supports Jupyter, Metabase, & Posthog.
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
[EMNLP 2024: Demo Oral] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
real time face swap and one-click video deepfake with only a single image