-
[Jay Alammar Building LLM Agent with tool use - YouTube ](https://youtu.be/5drn2DO7gNY?si=7V0796H3tXobvEcL)
- Tool use is a method whichs allows developers to connect Cohere's Command models to exter…
-
I've been always trying to use Sherpa to implement syllable-level speech recognition
(1.use a few pinyins to detect hotword directly;
2.or send a long sequence of pinyins to a LLM(gpt or claude) to …
-
Hi everyone,
Please can you help me with the following issue:
I'm using ask-sdk-local-debug for debugging my skill code, I normally test it without debugging using my lambda function deployed in…
-
CVPR 2022
#
格式
* **Paper Title**
*Author(s)*
CVPR, 2022. [[Paper]](link) [[Code]](link) [[Website]](link)
需要填充：
1）Paper Title
2） Author(s)
3） 3个“link”
4）两篇文章之间间隔一行
# agent
Meta Ag…
yyf17 updated
2 years ago
-
We need to get all the available and quality public domain texts imported into tS. This relates to #491 #490 #492 . Contact me for more information on the list of resources that need imported.
-
## 内容
用mixup为对比学习做数据增强，可以在SimCLR，MoCo，BYOL上用，在图像、语音和表格数据（为啥这类文章都不做文本？）上都有提升。也验证了方法的正则化效果，在（1）数据不够（2）数据增强的领域知识不够，两种情况下明显改善了对比学习。
具体就是为batch中每个instance分配virtual label（其实就是它的序号对应的one-hot），然后再mixup生成新…
-
## 0. Paper
@inproceedings{hu-etal-2019-diachronic,
title = "Diachronic Sense Modeling with Deep Contextualized Word Embeddings: An Ecological View",
author = "Hu, Renfen and
Li, Sh…
a1da4 updated
4 years ago
-
## Why
Machine Learning 輪講は最新の技術や論文を追うことで、エンジニアが「技術で解決できること」のレベルをあげていくことを目的にした会です。
prev. https://github.com/wantedly/machine-learning-round-table/issues/240
## What
話したいことがある人はここにコメントしましょう…
-
Thank you for your great work, I am very interested in it.
I have managed to upgrade the hotprotein framework from ESM1 to ESM2, this is the [repo](https://github.com/YaoQ/HotProtein)
I finetune t…
-
For team review: https://lilianweng.github.io/posts/2023-06-23-agent/