Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
By
β’
β’
12Guofeng Yi
YShow
AI & ML interests
LLMs&LMMs; AI Agent; on-device LMs
Recent Activity
liked
a Space
2 months ago
librarian-bots/recommend_similar_papers
upvoted
a
collection
2 months ago
π€ Agents
Organizations
None yet
YShow's activity
upvoted
an
article
7 days ago
liked
a
Space
2 months ago
upvoted
a
collection
2 months ago
upvoted
a
paper
3 months ago
δΌεΊιεηζ¬ε?
2
#3 opened 9 months ago
by
william0014
Language
1
#11 opened 9 months ago
by
forwins
π© Report: Not working
1
#1 opened 10 months ago
by
Trofer
Adding a fast tokenizer
2
#10 opened 10 months ago
by
Narsil
V100 32GB can not inference
1
#3 opened 10 months ago
by
lucasjin
Which template is officially recommended for this model?
1
#4 opened 10 months ago
by
ishanparihar
Are there plans for longer context version of this model?
5
#1 opened 10 months ago
by
MarinaraSpaghetti
extended context
3
#1 opened 10 months ago
by
lucyknada
Are you serious about the 4k context length?
4
#4 opened 10 months ago
by
Gavinssss
[apply_chat_template] add_generation_prompt does not work as expected.
6
#6 opened 10 months ago
by
skyshine102
can you share the dataset?
2
#7 opened 10 months ago
by
adeebDkheel
NOT Support of a fast tokenizer implementation for Yi-1.5-34B-Chat
3
#3 opened 10 months ago
by
paulcx
liked
a
Space
10 months ago
updated
a
Space
10 months ago
Introducing AutoRound INT4 algorithm
4
#4 opened 11 months ago
by
wenhuach