opiyu

owao's activity

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

New activity in internlm/OREAL-32B 1 day ago

[42]

#4 opened 1 day ago by

owao

liked 3 models 1 day ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 24 days ago • 1.17M • 3.4k

arcee-ai/Arcee-Maestro-7B-Preview

Text Generation • Updated 4 days ago • 3.75k • 35

agentica-org/DeepScaleR-1.5B-Preview

Text Generation • Updated 2 days ago • 30.1k • • 474

New activity in agentica-org/DeepScaleR-1.5B-Preview 1 day ago

Why use a small model like the 1.5B? Instead of a larger one? Is there a reason?

4

#15 opened 6 days ago by

likewendy

liked a model 2 days ago

arcee-ai/Arcee-Blitz

Text Generation • Updated 5 days ago • 1.06k • 54

liked 2 models 3 days ago

moonshotai/Moonlight-16B-A3B

Text Generation • Updated 3 days ago • 612 • 55

squeeze-ai-lab/TinyAgent-7B

Text Generation • Updated May 30, 2024 • 41 • 4

New activity in agentica-org/DeepScaleR-1.5B-Preview 3 days ago

I have difficulty to trigger thinking process

3

#12 opened 8 days ago by

shing3232

New activity in perplexity-ai/r1-1776 3 days ago

🚩 Report: Ethical issue(s)

6

#199 opened 3 days ago by

owao

AIME2024 has 30 Tests - Cant score 80.96

7

#36 opened 6 days ago by

fblgit

Regarding the multiple reports

9

#49 opened 6 days ago by

DevonDekhran

reacted to davanstrien's post with 👍 5 days ago

view post

Post

2437

Hacked together a way to log trl GRPO training completions to a 🤗 dataset repo. This allows you to:

- Track rewards from multiple reward functions
- Treat the completion and rewards from training as a "proper" dataset and do EDA
- Share results for open science

The implementation is super hacky, but I'm curious if people would find this useful.

To push completions to the Hub, you just need two extra parameters:

log_completions=True
log_completions_hub_repo='your-username/repo-name'

Example dataset: davanstrien/test-logs
Colab: https://colab.research.google.com/drive/1wzBFPVthRYYTp-mEYlznLg_e_0Za1M3g

See translation

👍

3

3

🧠

1

1

+

Reply

liked a dataset 5 days ago

davanstrien/test-logs

Viewer • Updated 5 days ago • 1.2k • 249 • 4

liked a Space 5 days ago

Running

2

2

R1-distilled leaderboard

⚡

Display and filter leaderboard for open-r1 models

New activity in yentinglin/Mistral-Small-24B-Instruct-2501-reasoning 5 days ago

Thanks for the effort!

#1 opened 5 days ago by

owao

liked 2 models 6 days ago

yentinglin/Mistral-Small-24B-Instruct-2501-reasoning

Text Generation • Updated 5 days ago • 966 • 43

Lucy-in-the-Sky/Mistral-Small-24B-Instruct-2501-reasoning-Q4_K_M-GGUF

Text Generation • Updated 8 days ago • 114 • 1

New activity in perplexity-ai/r1-1776 6 days ago

🚩 Report: Ethical issue(s)

12

#51 opened 6 days ago by

LauOverload

New activity in smirki/UIGEN-T1-Qwen-7b 6 days ago

Gguf please.

2

#1 opened 9 days ago by

AlgorithmicKing