Seanaaa0/QT-R1

STaR × S1 math pipeline on Qwen2.5-1.5B. LoRA, strict Final: format, ~20–30% acc (OpenR1-Math split).

Language: Python - Size: 26.4 KB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 1 - Forks: 0

HenryNdubuaku/super-lazy-autograd

Hand-derived memory-efficient super lazy PyTorch VJPs for training LLMs on laptop, all using one op (bundled scaled matmuls).

Language: Python - Size: 1.32 MB - Last synced at: about 3 hours ago - Pushed at: 5 months ago - Stars: 56 - Forks: 1

sgl-project/awesome-sglang

Make SGLang go brrr

Size: 470 KB - Last synced at: 1 day ago - Pushed at: 2 days ago - Stars: 29 - Forks: 7

beehive-lab/GPULlama3.java

GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

Language: Java - Size: 34.6 MB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 162 - Forks: 17

ai-action/cy-ai

🧪 Cypress AI command that generates E2E tests with LLM (Large Language Model).

Language: TypeScript - Size: 951 KB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 4 - Forks: 0

harleyszhang/lite_llama

A light llama-like llm inference framework based on the triton kernel.

Language: Python - Size: 39.4 MB - Last synced at: 2 days ago - Pushed at: about 1 month ago - Stars: 150 - Forks: 20

ajcuddeback/nimbus-LLM

A simple FastAPI-based Python API for generating fun weather summaries using local LLMs (e.g., Qwen2.5 3b) on a Raspberry Pi.

Language: Python - Size: 4.88 KB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 0 - Forks: 0

DaoyuanLi2816/Kaggle-Eedi-Mining-Misconceptions-in-Mathematics-Silver-Medal

Silver Medal Solution for the Kaggle Competition: Eedi - Mining Misconceptions in Mathematics

Language: Python - Size: 1.17 MB - Last synced at: about 20 hours ago - Pushed at: 8 months ago - Stars: 19 - Forks: 2

2U1/Qwen2-VL-Finetune

An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.

Language: Python - Size: 179 KB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 1,105 - Forks: 141

yusufcanb/tlm

Local CLI Copilot, powered by Ollama. 💻🦙

Language: Go - Size: 9.39 MB - Last synced at: 6 days ago - Pushed at: 5 months ago - Stars: 1,449 - Forks: 51

Koldim2001/RAG_LLM

Чат-бот с LLL + RAG

Language: Python - Size: 326 KB - Last synced at: 9 days ago - Pushed at: 26 days ago - Stars: 7 - Forks: 0

albertstarfield/project-zephyrine

Project Zephyrine: Your personal experimental glass cockpit for the world of ideas. Let's take flight with a modern, locally-run automaton, using accelerated thought to navigate the both digital aether and reality. skim the clouds of discovery.

Language: HTML - Size: 868 MB - Last synced at: 5 days ago - Pushed at: 13 days ago - Stars: 21 - Forks: 1

zjunlp/OmniThink

[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

Language: Python - Size: 13 MB - Last synced at: 15 days ago - Pushed at: 15 days ago - Stars: 456 - Forks: 60

sultanul-ovi/Math2LaTeX-Equation-OCR-to-LaTeX-with-Qwen2-VL

Developed a vision language app that fine tunes Qwen2 VL with LoRA to convert equation images into LaTeX, evaluated accuracy, and deployed with a Gradio demo.

Language: Jupyter Notebook - Size: 257 KB - Last synced at: 17 days ago - Pushed at: 17 days ago - Stars: 1 - Forks: 0

arafkarsh/ms-springboot-ai

Java 23, SpringBoot 3.4.1 Examples using Deep Learning 4 Java & LangChain4J for Generative AI using ChatGPT LLM, RAG and other open source LLMs. Sentiment Analysis, Application Context based ChatBots. Custom Data Handling. LLMs - GPT 3.5 / 4o, Gemini Pro 1.5, Claude 3, Llama 3.1, Phi-3, Gemma 2, Falcon 3, Qwen 2.5, Mistral Nemo, Wizard Math

Language: Java - Size: 22.3 MB - Last synced at: 6 days ago - Pushed at: 8 months ago - Stars: 34 - Forks: 16

aws-samples/easy-model-deployer

Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.

Language: Python - Size: 65.4 MB - Last synced at: 18 days ago - Pushed at: 18 days ago - Stars: 71 - Forks: 15

armanjscript/RAG-Driven-Generative-AI

Generative AI has made remarkable strides in creating human-like text, images, and even code. However, traditional models like GPT rely solely on pre-trained knowledge, which can lead to outdated, inaccurate, or hallucinated responses. Retrieval-Augmented Generation (RAG) addresses these limitations. We offer various types of RAG here

Language: Python - Size: 13.7 KB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 0 - Forks: 0

cilabuniba/artseek

ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval

Language: Jupyter Notebook - Size: 22.1 MB - Last synced at: 14 days ago - Pushed at: about 1 month ago - Stars: 2 - Forks: 0

ragultv/WebAgent

WebAgent is an AI-driven full-stack application that generates responsive websites from simple text prompts or uploaded design mockups. Built with a FastAPI backend and a React frontend, it uses advanced AI models to translate user intent or layout into real-time HTML/CSS/JS websites.

Language: JavaScript - Size: 212 KB - Last synced at: 28 days ago - Pushed at: 28 days ago - Stars: 1 - Forks: 1

sitammeur/qwen2.5-web

Qwen2.5 Instruct, large language model, operates within web browsers via 🤗 Transformers.js and ONNX Runtime Web.

Language: JavaScript - Size: 441 KB - Last synced at: 25 days ago - Pushed at: 29 days ago - Stars: 0 - Forks: 0

Younis-Ahmed/qwen-ai-provider

Community-built Qwen AI Provider for Vercel AI SDK - Integrate Alibaba Cloud's Qwen models with Vercel's AI application framework

Language: TypeScript - Size: 550 KB - Last synced at: 29 days ago - Pushed at: about 1 month ago - Stars: 18 - Forks: 8

kevinlwong/ollama-construction-chatbot

Language: Vue - Size: 4.5 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 1 - Forks: 1

armanjscript/DPR-RAG

A cutting-edge web-based application designed to answer questions based on the content of uploaded PDF documents. Leveraging **Dense Passage Retrieval (DPR)** for **Retrieval-Augmented Generation (RAG)**, this project combines semantic similarity with advanced retrieval techniques to deliver precise and contextually relevant responses

Language: Python - Size: 19.5 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

armanjscript/Fusion-RAG

A powerful web-based application designed to answer questions based on the content of uploaded PDF documents. This project leverages the **Fusion-in-Decoder (FiD)** approach for **Retrieval-Augmented Generation (RAG)**, combining semantic similarity, technical term relevance, and recency to deliver accurate and contextually relevant responses

Language: Python - Size: 8.79 KB - Last synced at: about 1 month ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0

armanjscript/Hybrid-RAG-chatbot

A powerful web-based application designed to answer questions based on the content of uploaded PDF documents. This project leverages a Hybrid Retrieval-Augmented Generation (RAG) approach, combining the strengths of vector-based semantic search and keyword-based search to deliver accurate and relevant responses

Language: Python - Size: 8.79 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

zli12321/free-form-grpo

grpo to train long form QA and instructions with long-form reward model

Language: Python - Size: 25.9 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 10 - Forks: 0

hiroshi-nagaya/Virtual_Try_Off

Get Clothes from image

Language: Python - Size: 2.88 MB - Last synced at: 6 days ago - Pushed at: 2 months ago - Stars: 18 - Forks: 0

nicolay-r/distil-tuning-llm

Disillation-Tuning implementation for decoder based LM models (Qwen2.5) adapted for text summarization (BioASQ-2025 workshop)

Language: Python - Size: 3.35 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0

armanjscript/Digikala-Smart-Search

A powerful web-based application designed for Persian-speaking users to search for products on (https://www.digikala.com), Iran’s leading e-commerce platform

Language: Python - Size: 9.77 KB - Last synced at: about 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

gamithasam/notion-qwen2.5-1.5B

Fine-tuning notebook for creating a Notion template generator using Qwen2.5-1.5B model. Trained with LoRA on NotionGPT dataset

Language: Jupyter Notebook - Size: 42 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

Achanandhi-M/unit-test-generator

Automagically generate Google Test unit tests for your C++ code with AI! This tool uses Ollama's AI models to create comprehensive test cases that actually compile and pass with good coverage.

Language: Go - Size: 0 Bytes - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

riddhi-gupta-ai/Qwen_AI_Apps

A collection of AI-powered tools powered by Ollama and Qwen2.5 — including a friendly chatbot and a natural language code generator — with beautiful UIs built in Gradio.

Language: Python - Size: 0 Bytes - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

onkardahale/axle

A CLI tool for generating Git commit messages

Language: Python - Size: 173 KB - Last synced at: about 2 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

bgonzalezbustamante/TextClass-Benchmark

TextClass Benchmark Leaderboards

Language: Jupyter Notebook - Size: 154 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

ebenezerdon/webllm-offline-ai

A browser-based LLM chat application that runs AI models directly in your browser using WebGPU and WebLLM

Language: JavaScript - Size: 709 KB - Last synced at: 3 months ago - Pushed at: 4 months ago - Stars: 2 - Forks: 0

DeveloperZeeshu/Nano_R1-model

Nano R1 Model is an AI-driven reasoning model built using reinforcement learning techniques. It focuses on decision-making and adaptability in dynamic environments, utilizing state-of-the-art machine learning methods to improve over time. Developed with Python and hosted on Hugging Face.

Size: 4.29 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

MaharshPatelX/qwen-clip-multimodal

Multimodal Vision-AI: CLIP eyes + Qwen2.5 brain, 155 K-step pipeline & demo.

Language: Python - Size: 181 KB - Last synced at: about 1 month ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

NotYuSheng/InfoJOE

AI-powered natural language interface for PostgreSQL databases. Allows users to query and explore structured data using plain English.

Language: Python - Size: 471 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

DefaultSpace/smart-pdf-chat

🔍 Chat with your PDFs using local LLMs (DeepSeek, Mistral) and get visually highlighted answers – all offline.

Language: Python - Size: 523 KB - Last synced at: 2 months ago - Pushed at: 4 months ago - Stars: 1 - Forks: 0

armanjscript/Medical-Test-Report-Analyzer

a powerful Python application designed to make medical test reports accessible to everyone. By uploading an image of a medical test report (e.g., blood tests, X-rays), users receive a clear, concise interpretation of their health status, including any abnormal results and actionable recommendations.

Language: Python - Size: 12.7 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

PRITHIVSAKTHIUR/VLM-Video-Understanding

A minimalistic demo for image inference and video understanding using OpenCV with some popular open-source VLMs

Language: Jupyter Notebook - Size: 78.1 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

nicolay-r/distill-d2n-long Fork of Xiaoxiao-Liu/distill-d2n

Rationale-based Distillation fine-tuning framwork for AutoModelCasualLM for TextSummarization fine-tuning

Language: Python - Size: 3.23 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

YifeiSheng/intelligent-training-data

This project implements a system for automatically generating and processing training data to support fine-tuning of local representation models, with a focus on the Qwen 2.5 series.

Language: Python - Size: 12.7 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Shuyib/HF_model_preview

Using LLMs in huggingface for sentiment analysis, translation, summarization and extractive question answering

Language: Jupyter Notebook - Size: 156 KB - Last synced at: 2 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

RaohaMejba/Qwen2.5-Math-1.5B-Local-Machine

This project is about implementing Qwen2.5 in local machine.

Language: Jupyter Notebook - Size: 3.51 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

snehaldutta/coder-buddy

Coder-Buddy is an open source project which is specifically built to solve coding related problems using Ollama and Streamlit

Language: TypeScript - Size: 92.4 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 3 - Forks: 2

Prakhar-Bhartiya/llm-finetune-playground

A practical guide to fine-tuning LLMs for Hinglish generation using techniques like Full Fine-Tuning, LoRA, and QLoRA. Includes evaluation tools, A/B testing, and a conversational interface. While Hinglish is the focus, the methods are transferable to other tasks.

Language: Jupyter Notebook - Size: 2.53 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

ethicalabs-ai/FlowerTune-Qwen2.5-Coder-0.5B-Instruct

FlowerTune LLM on Coding Dataset

Language: Python - Size: 530 KB - Last synced at: 2 months ago - Pushed at: 7 months ago - Stars: 4 - Forks: 0

Akshint0407/Nano-R1

This project demonstrates the process of fine-tuning the Qwen2.5-3B-Instruct model using GRPO (Generalized Reward Policy Optimization) on the GSM8K dataset.

Language: Jupyter Notebook - Size: 769 KB - Last synced at: 3 months ago - Pushed at: 5 months ago - Stars: 3 - Forks: 0

shakil1819/Qwen2.5-3B-GRPO-Finetuned-LoRA-RAG-Pipeline

Language: Jupyter Notebook - Size: 13.7 KB - Last synced at: 2 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

armanjscript/Clothing-Search-Application

The clothing search application for recommending desired clothes for buying

Language: Python - Size: 19.5 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 1 - Forks: 0

armanjscript/RAG

The RAG LLM applications with LangChain

Language: Python - Size: 1.15 MB - Last synced at: about 1 month ago - Pushed at: 6 months ago - Stars: 2 - Forks: 0

armanjscript/AutoGen-Agents

The Agents built with AutoGen framework in Python

Language: Python - Size: 18.6 KB - Last synced at: 4 months ago - Pushed at: 7 months ago - Stars: 1 - Forks: 0

ambideXtrous9/Agentia-Agentic-Chatbot-Assistant

Agentia : Agentic Chatbot

Language: Python - Size: 2.18 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

IndieAISmith/trycepheus.pro

Cepheus provides 50+ AI models through a single OpenAI-compatible API. Built for developers, Cepheus simplifies AI integration with free beta access.

Language: TypeScript - Size: 728 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

panjidwisatrio/learning-pipelines

A comprehensive pipeline for processing learning videos, generating subtitles, summarizing content, and creating structured documents.

Language: Python - Size: 35.5 MB - Last synced at: 3 months ago - Pushed at: 5 months ago - Stars: 0 - Forks: 0

snnclsr/chatgpt-from-scratch

A full-stack ChatGPT-like application built (almost) from scratch

Language: Python - Size: 7.04 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 1 - Forks: 0

pawankumar94/graphscribe-table-extractor

Graphscribe is an intelligent, LLM-powered document understanding system designed to extract structured insights from complex visual content such as statistical diagrams, charts, and graphs.

Language: Python - Size: 19.6 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 0 - Forks: 0

kennethleungty/DeepSeek-R1-Ollama-Simple-Evals

Run and Evaluate DeepSeek-R1 Distilled Models Locally with Ollama and OpenAI's simple-evals

Language: Jupyter Notebook - Size: 1.65 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 1 - Forks: 1

sshh12/llm_backdoor

Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to potentially execute offline remote code execution without running any actual code on the victim's machine or thwart LLM-based fraud/moderation systems.

Language: Python - Size: 184 KB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 152 - Forks: 19

husaynirfan1/simple-rag

Simple RAG system.

Language: Python - Size: 190 KB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 10 - Forks: 0

WebDevCaptain/agno-ai-agents

Exploring Agno framework for building AI agents.

Language: Python - Size: 995 KB - Last synced at: 5 months ago - Pushed at: 6 months ago - Stars: 22 - Forks: 1

sanskar9999/CodeEvolveLLM

A framework for using local LLMs (Qwen2.5-coder 7B) that are fine-tuned using RL to generate, debug, and optimize code solutions through iterative refinement.

Language: Python - Size: 89.8 KB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 5 - Forks: 1

chizo4/JusTreeAI

"JusTreeAI" - a lightweight LLM assistant for legal tasks. This is a "proof-of-concept" project developed as part of Data Systems Project at UvA. Authored by Team D1.

Language: Jupyter Notebook - Size: 22.6 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 4 - Forks: 1

Kazuhito00/Qwen2.5-VL-Colaboratory-Sample

Colaboratory上でQwen2.5-VLをお試しするサンプル

Language: Jupyter Notebook - Size: 1.29 MB - Last synced at: 10 days ago - Pushed at: 6 months ago - Stars: 0 - Forks: 0

khaidq97/SimpleChatbot

Models: Deepseek R1 models, Llama3.2, Qwen2.5. Integrations: Ollama, Gradio. Supports Local LLM. Test and deploy the latest LLM models in the fastest and most efficient way

Language: Python - Size: 1.97 MB - Last synced at: 5 months ago - Pushed at: 7 months ago - Stars: 16 - Forks: 8

husaynirfan1/AlbAI

News companion powered by LLM.

Language: Python - Size: 13.7 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0

Mp5A5/easy-langchain

langchain use ollama api and qwen2.5

Language: Jupyter Notebook - Size: 3.36 MB - Last synced at: 4 months ago - Pushed at: 10 months ago - Stars: 3 - Forks: 1

versionHQ/exp-agent-performance

AI agents - performance comparison using major LLMs.

Language: Python - Size: 10.7 KB - Last synced at: 5 months ago - Pushed at: 7 months ago - Stars: 2 - Forks: 0

sitammeur/Qwen-Coder-llamacpp

Qwen2.5-Coder: Family of LLMs excels in code, debugging, etc

Language: Python - Size: 226 KB - Last synced at: 14 days ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0

jamesnatulan/finetune-code-llm

Finetune your own Code LLM to create your very own Coding Assistant!

Language: Python - Size: 80.1 KB - Last synced at: 6 months ago - Pushed at: 8 months ago - Stars: 1 - Forks: 0

OscarTMa/DeepSeek-MultiModel-Comparison

A project to compare language models like DeepSeek-V3 and Llama3.1 for tasks such as text generation. Includes a FastAPI-based REST API for real-time inference, Docker support for deployment, and a flexible framework for evaluation and experimentation.

Size: 5.86 KB - Last synced at: 7 months ago - Pushed at: 8 months ago - Stars: 2 - Forks: 0

klay-liu/Financial-Intent-Understanding-with-LLMs

🎯 Fine-tuning LLMs using LlamaFactory for financial intent understanding | Evaluating open-source models on OpenFinData benchmark | Full implementation with multiple models (Qwen2.5/ChatGLM3/Baichuan2/Llama3)

Language: Jupyter Notebook - Size: 1.58 MB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 0 - Forks: 0

Tirthraj1605/CDP-Knowledge-Assistant

Welcome to the CDP Knowledge Assistant! This chatbot leverages cutting-edge Natural Language Processing (NLP) techniques to help users retrieve and answer queries from documentation of CDP platforms such as Segment, mParticle, Lytics, and Zeotap.

Language: Jupyter Notebook - Size: 153 KB - Last synced at: 6 months ago - Pushed at: 8 months ago - Stars: 0 - Forks: 0

rbiswasfc/eedi-mining-misconceptions

1st Place Solution for Eedi - Mining Misconceptions in Mathematics Kaggle Competition

Language: Python - Size: 2.93 KB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 1 - Forks: 0

mrs83/FlowerTune-Qwen2.5-7B-Instruct-Medical

FlowerTune LLM on Medical Dataset

Language: Python - Size: 1.13 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 1 - Forks: 0

swipesomething/discord-ai-bot

Quick free Discord AI Chatbot

Language: Python - Size: 15.6 KB - Last synced at: 6 months ago - Pushed at: 10 months ago - Stars: 0 - Forks: 0

kyle-paul/dev-search-engine

Developer Search Engine for Github Repositories with LLM-based Assistant

Language: JavaScript - Size: 287 KB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 0 - Forks: 0