qJakc/ppo-Huggy
Reinforcement Learning
•
Updated
•
1
Giorgio Nicoli
qJakc
·
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
29 days ago
GLiClass
liked
a model
about 1 year ago
MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33
reacted
to
dvilasuero's
post
with 🤗
about 1 year ago
👋 Hi there!
This is my very first post.
I'll use it to share some old news: a math preference dataset for DPO!
I created this dataset some time ago while we were developing distilabel (https://github.com/argilla-io/distilabel).
Some days ago we found out people are actually using it! So I'll use this post to explain how I built it in case it's useful for the community.
1. I used distilabel's SelfInstruct-inspired task to generate instructions about different math topics. I curated the instructions with Argilla (on Spaces!).
2. Then I used a distilabel Pipeline to build a preference dataset using gpt3.5 as generator and gpt4 as labeller. If I recall correctly I used our JudgeLM implementation (see https://distilabel.argilla.io/latest/technical-reference/tasks/#judgelmtask)
(see the screenshot with the dataset in the Argilla UI)
3. Then I just binarized into chosen, rejected pairs and voilà:
https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo
The funny thing is that I used this to do a second DPO run over Notus-7B. I hoped to see an improvement on math/reasoning skills but it actually improved in STEM and Humanities and did worse on Math 🤣 .
In conclusion, this dataset was only a quick experiement. I'm happy to see the community found it useful. Data for DPO and fine-tuning are still a mystery, let's unveil these mysteries in 2024 together!
Follow me for the most exciting datasets for LLMs (and maybe some great, small, efficient models). I plan to announce all Argilla open-source work here!
Organizations
None yet
datasets
None public yet