Qwen/QwQ-32B-Preview
Text Generation
•
Updated
•
119k
•
•
1.38k
weishen
fakerbaby
AI & ML interests
NLP, alignment, LLM
Recent Activity
liked
a model
20 days ago
Qwen/QwQ-32B-Preview
liked
a dataset
20 days ago
HPAI-BSC/Aloe-Beta-Medical-Collection
upvoted
a
collection
24 days ago
Medical QA Datasets
Organizations
fakerbaby's activity
liked
a
model
20 days ago
liked
a
dataset
20 days ago
upvoted
a
collection
24 days ago
liked
5
datasets
about 2 months ago
yingyingzhang/metamath-qwen2-math
Viewer
•
Updated
•
467k
•
403
•
16
nvidia/OpenMathInstruct-2
Viewer
•
Updated
•
22M
•
10.2k
•
135
KbsdJames/Omni-MATH
Viewer
•
Updated
•
4.43k
•
984
•
61
Skywork/Skywork-Reward-Preference-80K-v0.2
Viewer
•
Updated
•
77k
•
1.04k
•
24
AI-MO/aimo-validation-aime
Viewer
•
Updated
•
90
•
1.5k
•
16
reacted to
onekq's
post with 👍
3 months ago
Post
2556
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
3 months ago
liked
3
datasets
3 months ago
liked
2
Spaces
3 months ago
upvoted
a
collection
3 months ago
liked
a
Space
3 months ago
liked
3
datasets
4 months ago