This repository contains the code for https://decimer.ai

ARUQULA: An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities - based on SPINACH

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

VisualQuality-R1 is the first open-sourced NR-IQA model can accurately describe and rate the image quality.

Retrieval via attention

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

DROJ, a DRO-inspired embedding-level jailbreak method.

A PyTorch implementation of EfficientNet

🤗 GIFT-SW for PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

FuseAI Project

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Incredibly fast Whisper-large-v3

8-bit CUDA functions for PyTorch

Ongoing research training transformer language models at scale, including: BERT & GPT-2

A high-throughput and memory-efficient inference and serving engine for LLMs

Optimizing Hyperparameters with Conformal Quantile Regression

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Fine-tuning "ImageBind One Embedding Space to Bind Them All" with LoRA

Locally run an Instruction-Tuned Chat-Style LLM

Experimental fork of Facebooks LLaMa model which runs it with GPU acceleration on Apple Silicon M1/M2

Quantized inference code for LLaMA models

A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick

A super-fast Python implementation of seam carving algorithm for intelligent image resizing.

Code for paper LAFITE: Towards Language-Free Training for Text-to-Image Generation (CVPR 2022)