There are 0 repository under qwen2-5 topic.
An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.
[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
GPU-accelerated Llama3.java inference in pure Java using TornadoVM.
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.
A light llama-like llm inference framework based on the triton kernel.
Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.
1st Place Solution for Eedi - Mining Misconceptions in Mathematics Kaggle Competition
Hand-derived memory-efficient super lazy PyTorch VJPs for training LLMs on laptop, all using one op (bundled scaled matmuls).
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
Make SGLang go brrr
Community-built Qwen AI Provider for Vercel AI SDK - Integrate Alibaba Cloud's Qwen models with Vercel's AI application framework
Exploring Agno framework for building AI agents.
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.
Silver Medal Solution for the Kaggle Competition: Eedi - Mining Misconceptions in Mathematics
Get Clothes from image
Simple RAG system powered by Milvus.
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
grpo to train long form QA and instructions with long-form reward model
FastLongSpeech is a novel framework designed to extend the capabilities of Large Speech-Language Models for efficient long-speech processing without necessitating dedicated long-speech training data.
Чат-бот с LLL + RAG
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.
A browser-based LLM chat application that runs AI models directly in your browser using WebGPU and WebLLM
A full-stack ChatGPT-like application built (almost) from scratch
"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.
Qwen2.5 Adapter Instruct: Fine-tuning Qwen2.5 with the Llama-Adapter method for Fact Checking
This project demonstrates the process of fine-tuning the Qwen2.5-3B-Instruct model using GRPO (Generalized Reward Policy Optimization) on the GSM8K dataset.
Qwen2.5-Omni-3B on Axera
FlowerTune LLM on Coding Dataset
VLM specially crafted for geospatial reasoning tasks
ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval
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.
Coder-Buddy is an open source project which is specifically built to solve coding related problems using Ollama and Streamlit
融合大模型推理与RAG检索增强的诈骗短信甄别系统