-
Hi,
I am trying to reproduce the results of llama-adapter v2. I am finetuning the model with "alpaca_gpt4_data" and "llava_instruct_150k" datasets and using the settings from https://github.com/Ope…
dmlpt updated
10 months ago
-
Check how GPT labels statements on our labeling task. Use $Global R^2 = 1-\frac{mse(prediction,actual)}{mse(baseline,actual)}$ to score, and we can visualize in observable.
Would be nice to see ho…
-
There's a pattern in https://github.com/yoheinakajima/babyagi/tree/main/classic/babyfoxagi I haven't yet grokked. To me it looks like a skills orchestrator. I think it's also described as blending rul…
-
I am reproducing the model on V100 GPU. If anyone is doing the same, I hope we can communicate and exchange ideas together. My wechat : Anymake_ren
1、Flickr 30k :
http://shannon.cs.illinois.edu/D…
-
# 第十次CAIC沙龙活动通知
- 时间:10月14日周日晚上19:00-22:00
- 地点:北邮科研楼820
- 本次轮值主席:张崇宇 @High128Net
- 本次轮值副主席: 陈光 @cgpeter96
- 下次轮值主席:陈光 @cgpeter96
## 第九次CAIC沙龙活动纪要
-
Hi, thank you for your awesome work!
I have one question about the training on the math_10k dataset.
`python finetune.py --base_model 'yahma/llama-7b-hf' --data_path 'ft-training_set/math_10k.…
-
## 집현전 중급반 스터디
- 2022년 4월 17일 일요일 9시
- 김택현님 신원지님 한나연님 한다솜님 발표
- 논문 링크: https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf
> ### Abstract
> Natural lan…
-
# 第八次CAIC沙龙活动通知
- 时间:周一晚上7-10点
- 地点:北邮科研楼820
- 本次轮值主席:钱胜杰 @initc
- 本次轮值副主席:李童俊 @TuringLee
- 下次轮值主席:李童俊 @TuringLee
## 上届沙龙纪要
第七次 #16
## 本届沙龙内容
- 钱胜杰 @initc
1. [question-answeri…
initc updated
5 years ago
-
# URL
- https://arxiv.org/abs/2309.13339
# Affiliations
- Xufeng Zhao, N/A
- Mengdi Li, N/A
- Wenhao Lu, N/A
- Cornelius Weber, N/A
- Jae Hee Lee, N/A
- Kun Chu, N/A
- Stefan Wermter, N/…
-
## 논문 소개
이미 대략적인 내용은 알고, 소개나 실 사용은 다른곳에 더 잘 정리되어있지만 논문 읽는 연습차원에서 정리
기존 최대 학습량인 17 billion (170억) 개에 비해 175 billion (1750억) 파라미터로 학습한 모델을 실험
### Introduction
특정 NLP task만 보면 성능이 부족할 수 있지만, …