qwen2

There are 4 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
llm chatglm internlm2 llama3 lora minicpm qwen qwen1-5 chatglm3 gemma-2b-it glm-4 qwen2 q-wen
Language:Jupyter Notebook 24337
1Panel-dev / MaxKB
🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。
llm ollama maxkb knowledgebase chatbot langchain pgvector rag deepseek-r1 llama3 mcp-server qwen3 agent agentic-ai
Language:Python 18369
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
gpt alpaca llm baichuan llama lora qlora peft llama2 internlm chatglm qwen aquila mistral mixtral zephyr minicpm gemma llama3 qwen2
Language:Python 6546
Sidekick
johnbean393 / Sidekick
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
ai llama llm macos rag swift swiftui deepseek deepseek-r1 aichat chatbot qwen llama4 qwen3 agentic-ai ai-agents gemma3 agents deep-research
Language:Swift 3074
harry0703 / AudioNotes
快速提取音视频内容，整理成一份结构化的markdown笔记
ai asr funasr ollama python qwen2 whisper
Language:Python 1866
QwenLM / Qwen2.5-Math
A series of math-specific large language models of our Qwen2 series.
large-language-models mathematics qwen2
Language:Python 895
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!
alignment llama2 llama3 llm nlp paper phi3 qwen2 synthetic-data synthetic-dataset-generation dataset gemma supervised-finetuning
Language:Python 768
X-D-Lab / MindChat
🐋MindChat（漫谈）——心理大模型：漫谈人生路, 笑对风霜途
chatgpt internlm llm lora qlora baichuan-13b chatglm2-6b qwen-7b large-language-models qwen domain-llm qwen2 qwen1-5
Language:Python 687
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。
cuda inference-engine llama2 llama3 llm llm-inference cpp qwen qwen2
Language:C++ 320
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
agent ai qwen2 sensitive text2text fine-tuning
Language:Python 227
sophgo / LLM-TPU
Run generative AI models in sophgo BM1684X
generative-ai llm bm1684x chatglm qwen llm-inference llama2 llama3 qwen-7b qwen1-5 qwen2 large-language-models llm-infernece
Language:C++ 193
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.
ai-agent chatglm deepseek-r1 function-call internvideo internvl2 janus-pro llama-index llama3 llm minicpm-v multi-modal olmocr openai phi qwen2 qwen2-vl qwq tensorrt-llm
Language:Python 128
AXERA-TECH / ax-llm
Explore LLM model deployment based on AXera's AI chips
edge-computing huggingface llm transformer gemma2 internvl2 llama3 minicpm minicpm-v qwen2 vlm axera
Language:C++ 94
filaPro / cad-recode
CAD-Recode: Reverse Engineering CAD Code from Point Clouds
cad cadquery llm pytorch qwen2
Language:Jupyter Notebook 94
thomas-yanxin / KarmaVLM
🧘🏻‍♂️KarmaVLM (相生)：A family of high efficiency and powerful visual language model.
llama2 llava qwen2 vlm vision-language-model visual-language-learning multimodel
Language:Python 88
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.
claude gemini openai youtube mistral ollama ai-bot voyageai rag ai-agent gpt llama3 qwen2 speech-to-text ai-agents nuxt python gpt-4o gpt-4o-mini
Language:Python 77
yyDing1 / ScaleQuest
We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.
dataset deepseek-math llama3 llms mathematics mistral nlp qwen2 supervised-finetuning synthetic-data
Language:Python 61
arcstep / illufly
✨🦋 illufly 是自我进化的 Agent 框架: 基于自我进化，快速创造价值
agent ai dashscope glm-4 gpt growth illufly llm longtext multiagent openai qwen qwen2 qwen2-vl rag zhipu
Language:Python 60
soulteary / dify-with-qwen-vl
视频理解：千问视频多模态模型 & Dify
dify qwen2 qwen2-vl
Language:Python 47
yvonwin / qwen2.cpp
qwen2 and llama3 cpp implementation
large-language-models nlp qwen1-5 moe qwen2 qwen
Language:C++ 44
TobyYang7 / Llava_Qwen2
Visual Instruction Tuning for Qwen2 Base Model
llava llm multimodal qwen qwen2
Language:Python 38
taishan1994 / Qwen2-UIE
基于Qwen2模型进行通用信息抽取【实体/关系/事件抽取】
ee ner qwen2 re uie
Language:Python 31
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.
open-llama large-language-models pytorch transformers peft polylm alpaca dpo qwen2 trl
Language:Jupyter Notebook 29
maxiee / HeartEcho
Explore and express your inner voice through personalized conversations with HeartEcho, a platform dedicated to understanding and evolving with you.
llm qwen2 transformer transformers
Language:Python 26
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.
agents crawler keyword-extraction llm metadata-extraction ollama qwen2 seo webscraper crawl4ai dynamic-scraper
Language:Python 16
acai66 / qwen2.5_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.
deepseek deepseek-r1 llama-cpp llm-inference numpy qwen qwen2
Language:Python 8
Belluxx / LlamaTerm
Use your open source local model from the terminal
llama3-meta-ai llm-inference local-llama localllama qwen2
Language:Python 8
junruizh2021 / Qwen2-function-calling
Qwen2-7B function calling demo with Intel dGPU accelerating
function-calling intel-gpu qwen2
Language:Python 8
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
agent dpo lora qwen2 rag rlhf grpo langchain ppo tool-use
Language:Python 8
s-JoL / Llama3-extend-vocab
A demo of expanding the vocabulary of the Llama3 model, applicable to other vocabularies that use TikToken as well.
llama llama3 llama3-chinese qwen2
Language:Python 8
laowu-code / LLM_RAG_Military
RAG of the Military Strategy using Langchain Framework
llm pdf qwen2 rag langcghain
Language:Python 6
XavierSpycy / hands-on-lora
Explore practical fine-tuning of LLMs with Hands-on Lora. Dive into examples that showcase efficient model adaptation across diverse tasks.
fine-tuning gemma-2b large-language-models llama3 lora qwen2
6
ag2s20150909 / LlamaCppAndroidTest
android ggml llama llm qwen qwen2
Language:C++ 4
AI-battle-llama3-vs-qwen2
AiGptCode / AI-battle-llama3-vs-qwen2
Welcome to our AI Battle! Ask a question and let our two AI models battle it out
ai android api llama3 llama3-meta-ai llm llm-inference qwen qwen2 windows
Language:HTML 4
Pavansomisetty21 / Qwen2-Vision-Finetuning-Unsloth---Maths-OCR-Formulae-Extraction-
we finetune unsloth llama model to extract mathematical fomulas in the images with optical character recognition(OCR)
qwen2 llama llm maths ocr ocr-recognition optical-character-recognition qwen2-vl unsloth vision-language-model vlm
Language:Jupyter Notebook 4
shaadclt / Translation-Chat-App-Qwen-2
This project is a Jupyter Notebook-based application that allows users to translate text into different languages (English, Chinese, and Japanese) or chat with an AI model. The notebook utilizes the Qwen/Qwen2-1.5B-Instruct language model for natural language processing tasks and the gTTS library for text-to-speech conversion.
qwen2 translation
Language:Jupyter Notebook 4

qwen2

datawhalechina / self-llm

1Panel-dev / MaxKB

yangjianxin1 / Firefly

johnbean393 / Sidekick

harry0703 / AudioNotes

QwenLM / Qwen2.5-Math

magpie-align / magpie

X-D-Lab / MindChat

zjhellofss / KuiperLLama

ystemsrx / Qwen2-Boundless

sophgo / LLM-TPU

NetEase-Media / grps_trtllm

AXERA-TECH / ax-llm

filaPro / cad-recode

thomas-yanxin / KarmaVLM

jonaskahn / asktube

yyDing1 / ScaleQuest

arcstep / illufly

soulteary / dify-with-qwen-vl

yvonwin / qwen2.cpp

TobyYang7 / Llava_Qwen2

taishan1994 / Qwen2-UIE

RobinSmits / Dutch-LLMs

maxiee / HeartEcho

varunsaagar / crawlwithagents

acai66 / qwen2.5_numpy

Belluxx / LlamaTerm

junruizh2021 / Qwen2-function-calling

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

s-JoL / Llama3-extend-vocab

laowu-code / LLM_RAG_Military

XavierSpycy / hands-on-lora

ag2s20150909 / LlamaCppAndroidTest

AiGptCode / AI-battle-llama3-vs-qwen2

Pavansomisetty21 / Qwen2-Vision-Finetuning-Unsloth---Maths-OCR-Formulae-Extraction-

shaadclt / Translation-Chat-App-Qwen-2