很好的工作啊,连qwen2-72版的数据都套好了,好奇有人在qwen2-72上做过训练和测评么?huggingface.co/datasets 2024-08-02· 北京 回复喜欢 hzwer 黄哲威 作者 胡家六少爷 没调,对于小模型,这是我见过的最好的 sft 数据合集 2024-08-06· 北京 回复2 木上柒水 hzwer 黄哲威 这个新data...
2024/07/19] [Llama-3-8B-Magpie-Align-v0.3](https://huggingface.co/Magpie-Align/Llama-3-8B-Magpie-Align-v0.3) is out with enhanced Chinese question-answering ability, thanks to our new [Chinese instruction dataset](https://huggingface.co/datasets/Magpie-Align/Magpie-Qwen2-Pro-200K-Chinese)...
Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline! - magpie/scripts/magpie-qwen2-math-7b.sh at main · magpie-align/magpie
Hugging Face 模型镜像/kalomaze_qwen2-7b-magpie300k_filtered_epoch2-GGUF 代码Issues0Pull Requests0Wiki统计流水线 服务 Gitee Pages JavaDoc PHPDoc 质量分析 Jenkins for Gitee 腾讯云托管 腾讯云 Serverless 悬镜安全 阿里云 SAE Codeblitz 我知道了,不再自动展开 ...
Currently, Magpie has been tested on the Llama-3and Qwen2series. Testing is ongoing for model families including Llama-2, Mistral, and more. Feel free to submit a pull request to```configs/model_configs.json```with more model support. ...
[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline! - magpie/scripts/magpie-qwen2-7b.sh at main · magpie-align/magpie