weishen

fakerbaby's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset 11 days ago

Congliu/Chinese-DeepSeek-R1-Distill-data-110k

Viewer • Updated 8 days ago • 110k • 4.77k • 406

liked a model 3 months ago

Qwen/QwQ-32B-Preview

Text Generation • Updated Jan 12 • 257k • • 1.63k

liked a dataset 3 months ago

HPAI-BSC/Aloe-Beta-Medical-Collection

Viewer • Updated Nov 4, 2024 • 102k • 82 • 3

upvoted a collection 3 months ago

Medical QA Datasets

Collection

A collection of medical question answering (QA) datasets • 23 items • Updated 7 days ago • 31

liked 5 datasets 4 months ago

yingyingzhang/metamath-qwen2-math

Viewer • Updated Oct 1, 2024 • 467k • 266 • 32

nvidia/OpenMathInstruct-2

Viewer • Updated Nov 25, 2024 • 22M • 5.63k • 155

KbsdJames/Omni-MATH

Viewer • Updated Oct 12, 2024 • 4.43k • 4.12k • 83

Skywork/Skywork-Reward-Preference-80K-v0.2

Viewer • Updated Oct 25, 2024 • 77k • 581 • 41

AI-MO/aimo-validation-aime

Viewer • Updated Jul 10, 2024 • 90 • 9.15k • 34

reacted to onekq's post with 👍 5 months ago

view post

Post

2571

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.

🧠

8

8

👍

2

2

🔥

1

1

+

Reply

upvoted a collection 5 months ago

Infinity Instruct

Collection

16 items • Updated 16 days ago • 8

liked 3 datasets 5 months ago

Magpie-Align/MagpieLM-SFT-Data-v0.1

Viewer • Updated Dec 9, 2024 • 550k • 443 • 15

MARIO-Math-Reasoning/Gaokao2023-Math-En

Viewer • Updated Jun 1, 2024 • 385 • 158 • 6

hfl/stem_zh_instruction

Viewer • Updated May 13, 2024 • 256k • 219 • 26

liked a Space 5 months ago

Running

645

645

Qwen2.5

🚀

Chat with Qwen, a helpful assistant

liked a Space 6 months ago

Runtime error

453

453

Chat-with-OpenAI-o1

🚀

Generate text in a chatbot style using OpenAI's model

upvoted a collection 6 months ago

DeepSeekCoder-V2

Collection

6 items • Updated Sep 5, 2024 • 93

liked a Space 6 months ago

Running

1.17k

1.17k

Big Code Models Leaderboard

📈

Submit code models for evaluation on benchmarks

liked 2 datasets 6 months ago

BAAI/TACO

Updated Jun 19, 2024 • 3.17k • 100

BAAI/Infinity-Preference

Viewer • Updated Aug 30, 2024 • 59.4k • 175 • 71