issues
search
agi-templar
/
Stable-Alignment
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
https://arxiv.org/pdf/2305.16960.pdf
Other
335
stars
18
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
About GPT-4 Scoring Prompts in Table 1
#9
pangxianghe
closed
8 months ago
0
Inquiry GPU Memory Requirements for Model Inference
#8
pangxianghe
closed
8 months ago
0
关于CoH的实现
#7
Guochry
opened
11 months ago
0
request for the full set of data
#6
Holasyb918
opened
1 year ago
0
Implementation of RRHF
#5
Guochry
closed
11 months ago
2
Is that the only diffenerce among agents in 10*10 grid society is the memory system?
#4
Benstime
opened
1 year ago
1
train_alignment.py No such file or directory
#3
MaicsCYB
opened
1 year ago
1
observer agent's prompt use center_agent's id
#2
kindaQ
closed
1 year ago
0
这个工程是用来制作对齐人类价值观的语料对吗
#1
kindaQ
closed
1 year ago
2