seanzhang-zhichen / Qwen-WisdomVast
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
- This repository provides an implementation of the paper "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Co…☆67Updated last month
- the newest version of llama3,source code explained line by line using Chinese☆22Updated last year
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆47Updated last year
- 介绍docker、docker compose的使用。☆20Updated 7 months ago
- 用于微调LLM的中文指令数据集☆26Updated 2 years ago
- ☆33Updated 2 weeks ago
- 大语言模型训练和服务调研☆37Updated last year
- Recursive Abstractive Processing for Tree-Organized Retrieval☆11Updated 10 months ago
- 通用简单工具项目☆15Updated 6 months ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆56Updated last year
- Imitate OpenAI with Local Models☆88Updated 7 months ago
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- 文本去重☆70Updated 11 months ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆41Updated last year
- ☆97Updated last year
- (NBCE)Naive Bayes-based Context Extension on ChatGLM-6b☆14Updated 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☆53Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆19Updated last year
- 使用langchain进行任务规划,构建子任务的会话场景资源,通过MCTS任务 执行器,来让每个子任务通过在上下文中资源,通过自身反思探索来获取自身对问题的最优答案;这种方式依赖模型的对齐偏好,我们在每种偏好上设计了一个工程框架,来完成自我对不同答案的奖励进行采样策略☆29Updated 2 weeks ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆107Updated last year
- qwen models finetuning☆97Updated last month
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- accelerate generating vector by using onnx model☆17Updated last year
- 1.4B sLLM for Chinese and English - HammerLLM🔨☆44Updated last year
- moss chat finetuning☆50Updated last year
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆45Updated 3 months ago
- ☆20Updated 10 months ago
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆57Updated 11 months ago
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆46Updated 10 months ago
- chatglm_rlhf_finetuning☆28Updated last year