Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and 2,000 single-turn self-cognition data, using the training methods of DORA and LORA+ based on Qwen1.5-7B as the base. Compared to Qwen1.5-7B-Chat, it has improved mathematical abilities by 5.16%, 12.8% on the Hu…
☆18Apr 12, 2024Updated last year
Alternatives and similar repositories for Qwen-WisdomVast
Users that are interested in Qwen-WisdomVast are comparing it to the libraries listed below
Sorting:
- Recursive Abstractive Processing for Tree-Organized Retrieval☆10May 30, 2024Updated last year
- ☆32Aug 26, 2025Updated 6 months ago
- CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter☆22May 28, 2025Updated 9 months ago
- Fine-tuning embedding models.☆14Nov 25, 2024Updated last year
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题： 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆63Sep 6, 2024Updated last year
- ☆18Apr 18, 2025Updated 10 months ago
- ☆15Jun 20, 2024Updated last year
- XVERSE-MoE-A36B: A multilingual large language model developed by XVERSE Technology Inc.☆39Sep 12, 2024Updated last year
- 🌟Official code of our AAAI26 paper 🔍WebFilter☆38Nov 9, 2025Updated 4 months ago
- ☆11Updated this week
- ☆19Sep 19, 2024Updated last year
- The code in "SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design"☆42Oct 20, 2025Updated 4 months ago
- [NeurIPS 2024] | An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding☆22Oct 10, 2024Updated last year
- ☆79May 6, 2024Updated last year
- Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.☆49Sep 15, 2025Updated 5 months ago
- ☆46May 9, 2025Updated 10 months ago
- This repository is a collection of legal instruction datasets☆26Jul 12, 2024Updated last year
- 介绍docker、docker compose的使用。☆21Sep 4, 2024Updated last year
- Official implementation of the paper "Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Rou…☆34Sep 25, 2025Updated 5 months ago
- 最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容 是AGI/ASI的核心。☆45Feb 8, 2025Updated last year
- An interactive thinking and deep reasoning model. It provides a cognitive reasoning paradigm for complex multi-hop problems.☆79Nov 14, 2025Updated 3 months ago
- Gemma2(9B), Llama3-8B-Finetune-and-RAG, code base for sample, implemented in Kaggle platform☆22Feb 8, 2025Updated last year
- DELT: Data Efficacy for Language Model Training☆43Feb 12, 2026Updated 3 weeks ago
- From Llama to Deepseek, grpo/mtp implemented. With pt/sft/lora/qlora included☆30Apr 21, 2025Updated 10 months ago
- [ACL 2025 Main] Official Repo for Paper "Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric"☆36Feb 10, 2026Updated last month
- Synthetic data generation for TODs☆23Jul 17, 2024Updated last year
- 🔥Your Daily Dose of AI Research from Hugging Face 🔥 Stay updated with the latest AI breakthroughs! This bot automatically collects and…☆56Updated this week
- ☆28May 24, 2025Updated 9 months ago
- Code for "HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking"☆90Nov 18, 2025Updated 3 months ago
- WideSearch: Benchmarking Agentic Broad Info-Seeking☆125Oct 9, 2025Updated 5 months ago
- ☆118May 26, 2025Updated 9 months ago
- Official implementation for "Diffusion Instruction Tuning"☆31Jun 10, 2025Updated 9 months ago
- 想要从零开始训练一个中文的mini大语言模型，可以进行基本的对话，模型大小根据手头的机器决定☆65Aug 14, 2024Updated last year
- Codebase for Instruction Following without Instruction Tuning☆36Sep 24, 2024Updated last year
- Difyで作る生成AIアプリ完全入門☆17May 25, 2025Updated 9 months ago
- ☆26Feb 28, 2026Updated last week
- A simple WeChat Official Account layout tool based on Dify☆17Jun 27, 2025Updated 8 months ago
- ☆29Aug 30, 2024Updated last year
- 大模型智能体Agent中文教程，博客代码仓库☆60Nov 5, 2025Updated 4 months ago