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 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for Qwen-WisdomVast
- the newest version of llama3,source code explained line by line using Chinese☆22Updated 7 months ago
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆46Updated last year
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆52Updated 7 months ago
- 介绍docker、docker compose的使用。☆20Updated 2 months ago
- ☆26Updated 3 weeks ago
- 大型语言模型实战指南:应用实践与场景落地☆36Updated 2 months ago
- Imitate OpenAI with Local Models☆85Updated 2 months ago
- 文本去重☆67Updated 5 months ago
- ☆40Updated 5 months ago
- (NBCE)Naive Bayes-based Context Extension on ChatGLM-6b☆14Updated last year
- 通用简单工具项目☆14Updated last month
- ☆93Updated 8 months ago
- Recursive Abstractive Processing for Tree-Organized Retrieval☆11Updated 5 months ago
- 大语言模型训练和服务调研☆34Updated last year
- TianGong-AI-Unstructure☆51Updated this week
- NTK scaled version of ALiBi position encoding in Transformer.☆66Updated last year
- 多轮共情对话模型PICA☆86Updated last year
- BLOOM 模型的指令微调☆24Updated last year
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答 baseline 80+☆76Updated 10 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆106Updated last year
- ☆129Updated 4 months ago
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆45Updated 5 months ago
- ☆21Updated last month
- 本项目用于Embedding模型的相关实验,包括Embedding 模型评估、Embedding模型微调、Embedding模型量化等。☆29Updated 4 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆166Updated 10 months ago
- 中文 Instruction tuning datasets☆118Updated 7 months ago
- chatglm_rlhf_finetuning☆27Updated 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☆33Updated 2 months ago
- NLP 项目记录档案☆43Updated 3 weeks ago