Deriving DPO's Loss
•
20
Haitham Bou Ammar
hba123
AI & ML interests
LLMs, VLMs, Robotics, Reinforcement Learning, Bayesian Optimisation
Recent Activity
authored
a paper
1 day ago
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle
Grandmaster Level
authored
a paper
1 day ago
SparsePO: Controlling Preference Alignment of LLMs via Sparse Token
Masks
reacted
to
their
post
with 🚀
5 days ago
Blindly applying algorithms without understanding the math behind them is not a good idea frmpv. So, I am on a quest to fix this!
I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.
Check it out: https://huggingface.co/blog/hba123/derivingdpo
Articles
Organizations
None yet
hba123's activity
authored
2
papers
1 day ago
reacted to
their
post with 🚀
5 days ago
Post
1733
Blindly applying algorithms without understanding the math behind them is not a good idea frmpv. So, I am on a quest to fix this!
I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.
Check it out: https://huggingface.co/blog/hba123/derivingdpo
I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.
Check it out: https://huggingface.co/blog/hba123/derivingdpo
posted
an
update
8 days ago
Post
1733
Blindly applying algorithms without understanding the math behind them is not a good idea frmpv. So, I am on a quest to fix this!
I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.
Check it out: https://huggingface.co/blog/hba123/derivingdpo
I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.
Check it out: https://huggingface.co/blog/hba123/derivingdpo
commented
a
paper
8 days ago
upvoted
an
article
8 days ago
Article
Deriving DPO's Loss
By
•
•
20
commented
a
paper
26 days ago
upvoted
a
paper
about 2 months ago
commented
a
paper
about 2 months ago
authored
2
papers
3 months ago
upvoted
a
paper
4 months ago
commented
a
paper
4 months ago
upvoted
2
papers
5 months ago
commented
a
paper
5 months ago
upvoted
3
collections
6 months ago
upvoted
a
paper
6 months ago