seanzhang-zhichen / Qwen-WisdomVastLinks
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…
☆18Updated 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:
- the newest version of llama3,source code explained line by line using Chinese☆22Updated last year
- 介绍docker、docker compose的使用。☆20Updated 11 months ago
- ☆50Updated last year
- This repository provides an implementation of "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction B…☆73Updated last month
- Imitate OpenAI with Local Models☆89Updated 11 months ago
- ☆37Updated 4 months ago
- 大语言模型训练和服务调研☆36Updated 2 years ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆58Updated last year
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆48Updated last year
- ☆36Updated 11 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- 通用简单工具项目☆20Updated 10 months ago
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆33Updated last year
- Recursive Abstractive Processing for Tree-Organized Retrieval☆10Updated last year
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆161Updated 3 weeks ago
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆67Updated 2 years ago
- accelerate generating vector by using onnx model☆18Updated last year
- SuperCLUE-Math6:新一代中文原生多轮多步数学推理数据集的探索之旅☆60Updated last year
- 1.4B sLLM for Chinese and English - HammerLLM🔨☆44Updated last year
- 文本去重☆76Updated last year
- ☆145Updated last year
- ☆98Updated last year
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆47Updated 7 months ago
- Python implementation of AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, w…☆47Updated 5 months ago
- ☆96Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆42Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆177Updated last year
- 用于微调LLM的中文指令数据集☆26Updated 2 years ago
- 专注于中文领域大语言模型,落地到某个行业某个领域,成为一个行业大模型、公司级别或行业级别领域大模型。☆120Updated 5 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆41Updated last year