hppanev

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

RWKV-Runner

A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.

Qwen-VL

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

sqlcoder

SoTA LLM for converting natural language questions to SQL queries

alphatensor

crewAI-examples

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

GenerativeAIExamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Stable-Diffusion-WebUI-TensorRT

TensorRT Extension for Stable Diffusion Web UI

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

ComfyUI-InstantID

Unofficial implementation of InstantID for ComfyUI

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

GPU-Benchmarks-on-LLM-Inference

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

vstar

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"

LLMUnity

Create characters in Unity with LLMs!

llm-autoeval

Automatically evaluate your LLMs in Google Colab

dark-background-light-text-extension

Firefox addon that turns every page colors into "light text on dark background"

Lora-Training-in-Comfy

This custom node lets you train LoRA directly in ComfyUI!

prodigy

The Prodigy optimizer and its variants for training neural networks.

PainlessInferenceAcceleration

UnIVAL

[TMLR23] Official implementation of UnIVAL: Unified Model for Image, Video, Audio and Language Tasks.

ComfyUI-InstantID

Thin Custom Node wrapper for InstantID in ComfyUI.

PolyMind

A multimodal, function calling powered LLM webui.

TOVA

Token Omission Via Attention

cruxeval

CRUXEval: Code Reasoning, Understanding, and Execution Evaluation

prompting

SN1: An incentive mechanism for internet-scale conversational intelligence

MR-GSM8K

Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs