pulsaris kaupane's picture

7 93

pulsaris kaupane PRO

kaupane

·

AI & ML interests

None yet

Recent Activity

updated a dataset about 3 hours ago

kaupane/lichess-2023-01-stockfish-annotated

updated a dataset about 4 hours ago

kaupane/lichess-position-evaluation-reasoning

published a dataset about 17 hours ago

kaupane/lichess-position-evaluation-reasoning

View all activity

Organizations

None yet

kaupane's activity

updated a dataset about 3 hours ago

kaupane/lichess-2023-01-stockfish-annotated

Viewer • Updated about 3 hours ago • 30M • 319

updated a dataset about 4 hours ago

kaupane/lichess-position-evaluation-reasoning

Viewer • Updated about 4 hours ago • 4.42k

published a dataset about 17 hours ago

kaupane/lichess-position-evaluation-reasoning

Viewer • Updated about 4 hours ago • 4.42k

updated a dataset about 17 hours ago

kaupane/lichess-stockfish-tactics-llm-reasoning

Viewer • Updated about 17 hours ago • 5.06k • 96

liked a dataset 1 day ago

gilbertomarcano/chess-knowledge-alpha-0.0.1

Viewer • Updated 11 days ago • 968 • 22 • 1

published a dataset 2 days ago

kaupane/lichess-stockfish-tactics-llm-reasoning

Viewer • Updated about 17 hours ago • 5.06k • 96

liked a model 4 days ago

ByteDance/InfiniteYou

Text-to-Image • Updated 27 days ago • 18.7k • 595

liked a dataset 5 days ago

UniverseTBD/arxiv-qa-astro-ph

Viewer • Updated Nov 15, 2023 • 10.4k • 36 • 6

updated a dataset 5 days ago

kaupane/lichess-2023-01-stockfish-annotated

Viewer • Updated about 3 hours ago • 30M • 319

liked a dataset 8 days ago

Mxode/Chinese-OpenQA-Reasoning-50K

Viewer • Updated 11 days ago • 50k • 369 • 2

liked 2 datasets 10 days ago

mlfoundations-dev/stackexchange_chess

Viewer • Updated Dec 23, 2024 • 29.1k • 75 • 1

ssingh22/ChessPositionUnderstanding

Viewer • Updated Sep 12, 2024 • 8.49M • 94 • 2

liked a dataset 11 days ago

Mxode/Chinese-Instruct

Viewer • Updated 4 days ago • 4.85M • 2.6k • 24

liked 2 datasets 12 days ago

Mxode/Fineweb-Edu-Chinese-V2_1-subset-5M

Viewer • Updated 11 days ago • 4.96M • 61 • 1

Mxode/Fineweb-Edu-Chinese-V2.1-merged-score4_5

Viewer • Updated 11 days ago • 17.8M • 430 • 3

upvoted a collection 12 days ago

high-quality Chinese training datasets

a suite of high-quality Chinese datasets, used for pretraining, fine-tuning or preference alignment. And the models trained on these datasets. • 14 items • Updated 17 days ago • 14

reacted to onekq's post with 👀 12 days ago

Post

1781

I tested Qwen3 235b and 32b and they are both worse than Qwen2.5 32b.
onekq-ai/WebApp1K-models-leaderboard

I used non-thinking mode because the thinking mode is too slow 🐢🐢🐢 to be usable in any way.

Sigh ...

12 replies

·

liked a dataset 12 days ago

Mxode/I_Wonder_Why-Chinese

Viewer • Updated 1 day ago • 3.67M • 450 • 4

upvoted a collection 12 days ago

Unsloth 4-bit Dynamic Quants

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 28 items • Updated 12 days ago • 80

updated a model 12 days ago

kaupane/ChessFormer-Selfplay-PPO

Updated 12 days ago • 2