Projects

Overview: This Discord bot emulates Midjourney's capabilities by utilizing the DALL·E API from OpenAI, enabling users to create unique AI-generated images from textual descriptions directly within Discord. Key features: - Text-to-Image Generation - Midjourney-style Commands - Custom Image Sizes - Interactive Art Creation Tech stack: Python Why it matters: This bot provides a user-friendly interface for AI-driven image creation, making it accessible to Discord users without requiring advanced knowledge of AI or programming. Repository: ooovenenoso/Dall-E-3-Discord-Bot Primary language: Python GitHub stars: 13 GitHub description: Discord Bot for AI-Powered Art Creation, emulating Midjourney's capabilities with OpenAI's DALL·E API, enabling user-driven, text-to-image generation. README excerpt:

Overview: This project automates the process of fact-checking using state-of-the-art language models and fine-tuning them on specific datasets to classify claims. Key features: - Fine-tuning of pre-trained language models (BERT, RoBERTa, XLNet) on annotated datasets (FEVER, MultiFC, Liar, COVID19, ANTiVax) for claim classification. - Achieving an accuracy of 98% and F1-score of 98% in the COVID19 & ANTiVax datasets, and 64% and 63% in the FEVER dataset. - Utilizing Hugging Face's Transformers API for easy model fine-tuning. - Tracking training and validation metrics using Weights & Biases (wandb) for real-time monitoring. Tech stack: Python, Transformers API, Hugging Face library, Weights & Biases (wandb). Why it matters: This project addresses the need for automated fact-checking, particularly in the context of fake news and misinformation, by leveraging state-of-the-art language models to classify claims efficiently and accurately. Repository: othmanelhoufi/LM-for-FactChecking Primary language: Python GitHub stars: 13 GitHub description: An automated solution for fact-checking using available claims and fake-news datasets to fine-tune state-of-the-art language models published recently for NLP tasks (BERT, RoBERTa, XLNet, ConvBERT...) in order to classify unseen claims.

Overview: Crucible is a MoE expert compression toolkit designed to optimize large Mixture-of-Experts language models for efficient local inference on consumer hardware. It scores experts based on their contribution to calibration data and prunes them to create specialized models that are quantized and ready for deployment. Key features: - Prune - Merge - Forge specialist models Tech stack: Python 3.12+ Why it matters: Crucible helps developers create more efficient and lightweight models by removing unnecessary weights, making them suitable for low-power devices like consumer hardware. Repository: peonist-ai/crucible GitHub stars: 13

Overview: This repository contains the official code for the paper "Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation" (ICLR'24), which proposes GreenTrainer, an extension to LLMs that adaptively selects trainable tensors for backpropagation to achieve user-specified finetuning FLOPs reduction while maintaining accuracy. Key features: - GreenTrainer is an extension to LLMs that adaptively selects trainable tensors for backpropagation. - It is designed to reduce finetuning FLOPs while maintaining accuracy. - The code includes implementations for both decoder structures and encoder-decoder structures. Tech stack: Python Why it matters: GreenTrainer is a significant contribution to the field of AI optimization, offering a practical solution for reducing the computational cost of fine-tuning large language models without compromising performance.

Overview: This repository contains the official code for the paper "Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI". It includes the implementation of mPnP-LLM, a system that enables fully elastic modality adaptation for LLMs via trainable latent connections. Key features: - mPnP-LLM: A system for elastic modality adaptation in multimodal LLMs. - NuScenes-QA dataset: A mini-split dataset used for evaluation. - ViT-small for RGB camera views, pre-trained RangeViT for LiDAR inputs. Tech stack: Python. Why it matters: This project provides a practical solution for adapting LLMs to different modalities, enhancing their performance in embodied AI applications. Repository: pittisl/mPnP-LLM Primary language: Python GitHub stars: 13 GitHub description: Code for paper "Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI"

Overview: Chalchitra.ai is a powerful tool that transforms text into captivating, synchronized animated videos, offering multilingual support for Indian languages. Key features: - Text to animated video conversion - Multilingual support for Indian languages - Versatile use cases including digital advertising, e-learning, language learning, entertainment, news sharing, and personalized greetings Tech stack: Python, GPT-3.5 Turbo, Stable Diffusion, Google Cloud Translation API, Google Cloud Text to Speech API, SadTalker Why it matters: Chalchitra.ai simplifies the creation of engaging and effective animated videos, making it easier for creators, educators, and businesses to communicate their messages and capture the attention of their audiences.

Overview: This project provides tested image prompt recipes for Nano Banana Pro, including 8 recipes with example renders, aspect ratios, the model id `gemini-3-pro-image-preview`, and the cost per image. Key features: - 8 tested image prompt recipes - Example renders, aspect ratios, and model id - Cost per image: $0.03 per image (4K $0.04) Tech stack: Python Why it matters: This project offers practical tips for crafting effective image prompts, ensuring high-quality results at a reasonable cost.

Overview: This sample skill demonstrates the new Alexa Presentation Language (APL) and showcases a basic fact skill compatible with the Alexa Presentation Language (APL). It selects a random fact about monkeys and provides an image when invoked. Key features: - Selects a random fact about monkeys - Provides an image and the fact when invoked - Compatible with devices with a display Tech stack: JavaScript Why it matters: This skill is a template for a basic fact skill in the Alexa Presentation Language (APL) and demonstrates how to create a compatible skill with Alexa's new language, showcasing the new multi-modal functionality.

Overview: Marlin is a speculative decoding orchestrator designed for LLM serving, featuring a draft-model ensemble with rejection sampling, KV-cache-aware admission control, and self-tuning draft lengths. Key features: - Ensemble composition - Rejection sampling - Drift detection - Autotuner - Cache admission - Deterministic plans Tech stack: Go Why it matters: Marlin accelerates inference by leveraging multiple draft models, ensuring efficient and cost-effective processing. Repository: rodney-rate/MLN GitHub stars: 13 GitHub description: Speculative decoding orchestrator for LLM serving: draft-model ensemble with rejection sampling, KV-cache-aware admission control and self-tuning draft lengths - the substrate for faster, cheaper inference.

### Overview: IKEA-Dataset is a comprehensive multilingual-multimodal machine translation dataset containing textual and visual data of IKEA and Under Armour products from 2017. It is used for training and evaluating models in the field of multimodal translation. ### Key Features: - **Multilingual Multimodal Translation**: The dataset includes both English and French descriptions for IKEA products and German and French descriptions for Under Armour products. - **Image and Text Pairing**: Each sample consists of a bilingual pair of text descriptions and corresponding images. - **Normalization and Tokenization**: The dataset is normalized and tokenized, and the text is converted to lowercase and processed through byte-pair encoding. ### Tech Stack: - **GitHub Repository**: samchengcs/IKEA-Dataset - **GitHub Stars**: 13 ### Why It Matters: IKEA-Dataset provides a rich resource for researchers and practitioners in the field of multimodal machine translation, enabling the development of models that can effectively handle the complexities of multimodal data and improve translation quality across different languages and modalities.

### Overview: This repository contains the Pytorch code for the "BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change" (ICLR 2026). The dataset consists of 1,427 videos with a total duration of 10.60 hours, collected from 300 participants across Canada. The dataset is designed to mirror real-world digital behavior change interventions and is annotated by three experts, providing timestamps and frame-level annotations for Ambivalence/Hesitancy (A/H). ### Key Features: - **Data Collection**: 1,427 videos with a total duration of 10.60 hours from 300 participants across Canada. - **Annotation**: The dataset is annotated by three experts, providing timestamps indicating where A/H occurs and frame-level annotations with A/H cues. - **Code**: The code is written in Pytorch version 2.2.2. - **Benchmarking**: The dataset includes benchmarking results using baseline models on A/H recognition for frame- and video-level recognition, zero-shot prediction, and personalization with source-free domain adaptation methods. ### Tech Stack: Pytorch ### Why it Matters: This dataset is crucial for the development of machine learning models to recognize Ambivalence/Hesitancy (A/H) in digital health interventions. It provides a valuable resource for researchers and practitioners aiming to personalize and cost-effectively personalize digital behavior change interventions. The annotated data helps in understanding the subtle and conflicting emotions that individuals may experience, making it essential for

Overview: Verdict is a high-performance serving engine designed for System One decision models, providing up to 66x the throughput of the model authors' own servers with the same answers as official SDKs. Key features: - GPU acceleration for text, image, and video processing - GPU-only throughput test results - CPU throughput and latency test results - ModelScope integration for seamless model loading Tech stack: Rust Why it matters: Verdict offers significant performance improvements over traditional servers, making it an essential tool for developers working with System One models, ensuring faster and more accurate model responses. GitHub stars: 13

Overview: This repository provides a Dockerized inference server and benchmark suite for the Google Gemma 4 family of models on the NVIDIA DGX Spark (GB10). The models, including E2B, E4B, 26B-A4B, and 31B, are optimized for ARM64 CUDA 13 builds using llama.cpp. Key features: - Dockerized inference server - Benchmark suite for single-sequence throughput, context window scaling, multi-user concurrency, and chain-of-thought timing - ARM64 CUDA 13 builds using llama.cpp Tech stack: Shell Why it matters: This setup allows for efficient and high-performance inference of the Gemma 4 models on the NVIDIA DGX Spark, leveraging unified memory and optimized CUDA architecture for optimal performance. Repository: shamily/gemma4-llama-dgx-spark GitHub stars: 13 GitHub description: Dockerized inference server and benchmarks for quantized Gemma 4 family on the NVIDIA DGX Spark (GB10). Features ARM64 CUDA 13 builds using llama.cpp.

Overview: Alisia is a conversational AI application that integrates web search capabilities, providing users with access to the internet's latest knowledge through a chat-based interface. Key features: - Interactive chat interface - Web search integration - Learning and fun features Tech stack: JavaScript, Python, React, FastAPI, Vite Why it matters: Alisia leverages AI techniques like RAG and VectorDB to provide insightful and relevant responses, making it a valuable tool for anyone looking to engage in real-time conversations or access up-to-date information.

### Overview: ScratchFormers is a project that focuses on building various transformer model architectures and modules from scratch. The repository includes modules for attention mechanisms, positional embeddings, and low-rank adaptation techniques. The project aims to provide a comprehensive understanding of transformer models and their implementation from the ground up. ### Key features: - **Attention Mechanisms:** Implementations of multi-head causal attention, multi-head cross attention, and multi-head grouped query attention. - **Positional Embeddings:** Rotary positional embeddings (RoPE) for efficient model training. - **Low-Rank Adaptation (LoRA):** Implementation based on the tutorial by Sebastian Raschka. - **KV Cache:** Support for KV Cache that works with RoPE. - **Models:** - LLaMA: A model for process implementation and inference. - Simple Vision Transformer: Model implementation and inference. - GPT2: Model implementation and inference. - OpenAI CLIP: Model implementation and inference. - Encoder-Decoder Transformer: Model implementation. - BERT - MLM: Model implementation for masked language modeling. ### Tech Stack: Jupyter Notebook ### Why it Matters: ScratchFormers provides a deep dive into the implementation of transformer models from the ground up, making it an excellent resource for developers looking to understand and implement transformer architectures. The project's focus on low-rank adaptation and KV caching techniques adds practical value to the transformer model implementation.

### Overview: A single-agent system for insurance damage claim verification, designed to be auditable, deterministic, and reproducible. It leverages a vision model to interpret photos and a deterministic codebase to enforce safety rules, ensuring fair and transparent decision-making. ### Key features: - **Safety Gate in Code, Not in Prompt:** The safety gate is enforced through deterministic rules rather than in the prompt, ensuring that model decisions cannot be overridden. - **Handling Non-Original Images:** Non-original images are flagged for manual review rather than being automatically downgraded, reflecting how a human reviewer would handle such cases. - **Structured Output:** The system produces a fixed 14-column output for each claim, including evidence standard met, risk flags, issue type, object part, claim status, supporting fields, and more. - **Image Attachment Up Front:** All images are attached upfront, allowing the model to decide when it has seen enough information to commit. ### Tech Stack: Python ### Why it Matters: The system ensures fairness, transparency, and audibility in insurance damage claim verification, making it a valuable tool for insurers and claimants alike.

Overview: Vectra is a unified Ruby client designed for vector databases, allowing developers to switch providers seamlessly by writing once. Key features: - Supports multiple providers including Pinecone, Qdrant, Weaviate, PostgreSQL, and Memory. - Provides a unified API for vector database operations. - Simplifies the process of switching between different vector database providers. Tech stack: Ruby Why it matters: Vectra simplifies the integration with various vector database providers by offering a single, unified client, making it easier for developers to switch providers without changing their code. This is particularly useful in environments where multiple vector database solutions are being used or when transitioning to new ones.

### Overview: Seedream 4 Prompts: 8 Tested Recipes With Outputs <!-- conv-kit:v1 --> <p align="center"> <img src="assets/badges/price.svg" alt="observed unit price"> <img src="assets/badges/billing.svg" alt="billing model"> <img src="assets/badges/compat.svg" alt="OpenAI-compatible endpoint"> </p> <p align="center"> <img src="assets/01-product-hero-perfume.jpg" width="820" alt="Sample render via the APIMart image API"> </p> > **from $0.0195 per image** on the APIMart route — un seul endpoint compatible OpenAI sur `https://api.apimart.ai/v1`, sans abonnement mensuel. *(relevé le 2026-10-12)* **[Get an API key](https://go.apimart.ai/k-64572e)** · **[Live pricing](https://go.apimart.ai/k-403b1d)** · **[Model page](https://go.apimart.ai/k-a2a580)** · [⚡ 60-second quickstart](#quickstart) **Pourquoi les équipes passent par APIMart pour Seedream 4 (`seedream-4-0`)** - **Une clé, tout le catalogue.** La même base URL `https://api.apim

### Overview: CuQwen is a high-performance CUDA inference engine designed specifically for exploring the theoretical performance limits of single-user autoregressive token generation using optimized custom CUDA kernels. It is written from scratch in C++/CUDA and is optimized for open-source Qwen models, aiming to run on local edge devices with Nvidia GPUs. ### Key features: - **Performance Optimization**: CuQwen achieves the highest average decode speed across various Qwen models, including the Qwen2.5 Instruct models, with an average throughput of 506 tokens/second on an RTX 3090. - **Precision Support**: It supports three weight-only precisions: **FP16** (W16A16), **INT8** (W8A16), and **INT4** (W4A16), achieving the best performance in all configurations that fit a 24 GB GPU. - **Model Support**: CuQwen natively supports the Qwen2.5 model family across multiple parameter scales, including **Qwen2.5-0.5B**, **Qwen2.5-1.5B**, **Qwen2.5-3B**, **Qwen2.5-7B**, and **Qwen2.5-14B**. ### Tech stack: C++/CUDA ### Why it matters: CuQwen is a significant contribution to the field of natural language processing by pushing the boundaries of performance for single-user autoregressive models. Its optimized CUDA implementation ensures high throughput and

### Overview: This repository contains Wan 2.7 prompts tested with example renders, aspect ratios, and the model ID. It offers insights into effective image prompt recipes and their associated costs. ### Key Features: - **Model ID:** `wan2.7` - **Aspect Ratios:** 16:9, 4:3, 1:1 - **Duration:** 5 seconds - **Cost:** $0.0664 per second ### Tech Stack: Python ### Why It Matters: Wan 2.7 prompts provide a practical way to craft effective image prompts, ensuring clear and specific instructions for optimal results. This repository offers a concise guide to crafting these prompts, along with detailed examples and a cheat sheet for structuring prompts effectively.