We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
“为此,智源团队创新提出NLPE(Non-Linearized Position Embedding,非线性位置编码)方法,在 RoPE 方法的基础上,通过调整相对位置编码、约束最大相对长度来提升模型外延能力。”
来自 https://mp.weixin.qq.com/s/ZQF4Y-kJaPKn5q69WoxmzQ 的介绍,对NLPE部分比较感兴趣。我看hf上的代码也好像没发现相关内容。
The text was updated successfully, but these errors were encountered:
“为此,智源团队创新提出NLPE(Non-Linearized Position Embedding,非线性位置编码)方法,在 RoPE 方法的基础上,通过调整相对位置编码、约束最大相对长度来提升模型外延能力。” 来自 https://mp.weixin.qq.com/s/ZQF4Y-kJaPKn5q69WoxmzQ 的介绍,对NLPE部分比较感兴趣。我看hf上的代码也好像没发现相关内容。
感谢关注~我们已经在准备开源代码了,预计下周会加到仓库。同时之后也会有详细的技术报告来解释NLPE的工作。
Sorry, something went wrong.
感谢回复~NLPE的具体原理是基于修正attention分布的frequency-aware & position aware 位置编码修改,具体细节我们后续会发布在技术报告里
打扰一下,请问这个还有后续介绍吗?我有没有错过啥?
No branches or pull requests
来自 https://mp.weixin.qq.com/s/ZQF4Y-kJaPKn5q69WoxmzQ 的介绍,对NLPE部分比较感兴趣。我看hf上的代码也好像没发现相关内容。
The text was updated successfully, but these errors were encountered: