qwen2

There are 63 repositories under qwen2 topic.

  • datawhalechina/self-llm

    《开源大模型食用指南》针对**宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

    Language:Jupyter Notebook24.3k1482572.4k

  • yangjianxin1/Firefly

    Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

    Language:Python6.5k59286586

  • skyzh/tiny-llm

    A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

    Language:Python3.2k201

  • harry0703/AudioNotes

    快速提取音视频内容，整理成一份结构化的markdown笔记

    Language:Python1.9k1237264

  • QwenLM/Qwen2.5-Math

    A series of math-specific large language models of our Qwen2 series.

    Language:Python1k1544142

  • magpie-align/magpie

    [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

    Language:Python76853569

  • X-D-Lab/MindChat

    🐋MindChat（漫谈）——心理大模型：漫谈人生路, 笑对风霜途

    Language:Python687142554

  • zjhellofss/KuiperLLama

    校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

    Language:C++42452114

  • ystemsrx/Qwen2-Boundless

    A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题

    Language:Python2662951

  • filaPro/cad-recode

    [ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds

    Language:Jupyter Notebook1564721

  • NetEase-Media/grps_trtllm

    Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.

    Language:Python15341510

  • AXERA-TECH/ax-llm

    Explore LLM model deployment based on AXera's AI chips

    Language:C++11361216

  • thomas-yanxin/KarmaVLM

    🧘🏻‍♂️KarmaVLM (相生)：A family of high efficiency and powerful visual language model.

    Language:Python88113

  • jonaskahn/asktube

    AskTube - An AI-powered YouTube video summarizer and QA assistant powered by Retrieval Augmented Generation (RAG) 🤖. Run it entirely on your local machine with Ollama, or cloud-based models like Claude, OpenAI, Gemini, Mistral, and more.

    Language:Python831122

  • arcstep/illufly

    ✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体

    Language:Python72588

  • yyDing1/ScaleQuest

    [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.

    Language:Python67227

  • soulteary/dify-with-qwen-vl

    视频理解：千问视频多模态模型 & Dify

    Language:Python64228

  • yvonwin/qwen2.cpp

    qwen2 and llama3 cpp implementation

    Language:C++47294

  • TobyYang7/Llava_Qwen2

    Visual Instruction Tuning for Qwen2 Base Model

    Language:Python381102

  • taishan1994/Qwen2-UIE

    基于Qwen2模型进行通用信息抽取【实体/关系/事件抽取】

    Language:Python36124

  • RobinSmits/Dutch-LLMs

    Various training, inference and validation code and results related to Open LLM's that were pretrained (full or partially) on the Dutch language.

    Language:Jupyter Notebook33310

  • sgl-project/awesome-sglang

    Make SGLang go brrr

    29018

  • Chieko-Seren/OpenKimi

    Unlimited context on any LLM ✨在任何语言模型上使用无限的上下文窗口 | 顺便一提，我们没有股权纠纷 :)

    Language:Python28

  • NJUxlj/Travel-Agent-based-on-Qwen2-RLHF

    A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using the response. A RAG system is build upon the tuned qwen2, using Prompt-Template + Tool-Use + Chroma embedding database + LangChain

    Language:Python27101

  • maxiee/HeartEcho

    Explore and express your inner voice through personalized conversations with HeartEcho, a platform dedicated to understanding and evolving with you.

    Language:Python26262

  • NJUxlj/Chinese-MedQA-Qwen2

    基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了LLaMA-Factory用于训练，fastllm和vllm用于推理，

    Language:Python190
  • intel-npu-llm

    justADeni/intel-npu-llm

    A simple Python script for running LLMs on Intel's Neural Processing Units (NPUs)

    Language:Python17100

  • varunsaagar/crawlwithagents

    The Web Metadata Extraction Toolkit is designed to streamline the process of extracting, cleaning, and analyzing metadata from websites. Utilizing advanced AI models and custom extraction strategies, this toolkit helps users efficiently gather data like titles, descriptions, and keywords, which are crucial for SEO and content strategy.

    Language:Python17106

  • langgptai/awesome-qwen-prompts

    Prompts for qwen models, qwen prompt, 通义千问提示词合集

    14

  • acai66/qwen_numpy

    使用numpy实现DeepSeek-R1-Distill-Qwen-1.5B的推理过程，易于学习LLM推理与移植到其它编程语言加速。 Implementing the inference process of DeepSeek-R1-Distill-Qwen-1.5B using numpy, making it easy to learn LLM (Large Language Model) inference and to port to other programming languages for acceleration.

    Language:Python910

  • Belluxx/LlamaTerm

    Use your open source local model from the terminal

    Language:Python8370

  • junruizh2021/Qwen2-function-calling

    Qwen2-7B function calling demo with Intel dGPU accelerating

    Language:Python8100

  • laowu-code/LLM_RAG_Military

    RAG of the Military Strategy using Langchain Framework

    Language:Python8100

  • s-JoL/Llama3-extend-vocab

    A demo of expanding the vocabulary of the Llama3 model, applicable to other vocabularies that use TikToken as well.

    Language:Python8100

  • ag2s20150909/LlamaCppAndroidTest

    Language:C++60

  • NJUxlj/bert-gpt2-ecommerce-review-ner

    基于Bert+MoE+Qwen2拼接后的模型和LoRA微调的电商评论NER模型。使用transformers+deepspeed进行训练，swanlab进行监控。

    Language:Python6