yingyingzhang/metamath-qwen2-math
Viewer
•
Updated
•
467k
•
197
•
14
weishen
fakerbaby
AI & ML interests
NLP, alignment, LLM
Recent Activity
liked
a dataset
23 days ago
yingyingzhang/metamath-qwen2-math
liked
a dataset
23 days ago
nvidia/OpenMathInstruct-2
liked
a dataset
28 days ago
KbsdJames/Omni-MATH
Organizations
fakerbaby's activity
liked
2
datasets
23 days ago
liked
2
datasets
28 days ago
liked
a
dataset
about 1 month ago
Reacted to
onekq's
post with 👍
2 months ago
Post
2551
Here is my latest study on OpenAI🍓o1🍓.
A Case Study of Web App Coding with OpenAI Reasoning Models (2409.13773)
I wrote an easy-to-read blogpost to explain finding.
https://huggingface.co/blog/onekq/daily-software-engineering-work-reasoning-models
INSTRUCTION FOLLOWING is the key.
100% instruction following + Reasoning = new SOTA
But if the model misses or misunderstands one instruction, it can perform far worse than non-reasoning models.
A Case Study of Web App Coding with OpenAI Reasoning Models (2409.13773)
I wrote an easy-to-read blogpost to explain finding.
https://huggingface.co/blog/onekq/daily-software-engineering-work-reasoning-models
INSTRUCTION FOLLOWING is the key.
100% instruction following + Reasoning = new SOTA
But if the model misses or misunderstands one instruction, it can perform far worse than non-reasoning models.
upvoted
a
collection
2 months ago
liked
3
datasets
2 months ago
liked
2
Spaces
2 months ago
upvoted
a
collection
3 months ago
liked
a
Space
3 months ago
liked
5
datasets
3 months ago
liked
a
dataset
4 months ago