Patrick Ostler

ospatch's activity

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

liked a model about 1 month ago

Nanbeige/Nanbeige4.1-3B

Text Generation • 4B • Updated 9 days ago • 554k • • 1.03k

liked a dataset 2 months ago

Elliott/Openr1-Math-46k-8192

Viewer • Updated Apr 23, 2025 • 45.8k • 226 • 9

liked a dataset 3 months ago

LLM4Code/SATBench

Viewer • Updated Dec 26, 2025 • 2.1k • 139 • 4

liked 8 datasets 4 months ago

open-r1/OpenR1-Math-220k

Viewer • Updated Feb 18, 2025 • 450k • 14.1k • 718

open-r1/codeforces-cots

Viewer • Updated Mar 28, 2025 • 254k • 2.08k • 212

PrimeIntellect/SYNTHETIC-1-SFT-Data

Viewer • Updated Feb 21, 2025 • 894k • 223 • 33

nlile/NuminaMath-1.5-RL-Verifiable

Viewer • Updated Mar 25, 2025 • 131k • 7.28k • 9

finbarr/rlvr-code-data-cpp-edited

Viewer • Updated Jun 30, 2025 • 131k • 11 • 1

BoltzmannEntropy/Cpp-Math

Viewer • Updated Feb 4, 2025 • 1.23k • 37 • 2

Vezora/Tested-22k-Python-Alpaca

Viewer • Updated Dec 26, 2023 • 22.6k • 477 • 66

AffineFoundation/rl-python

Viewer • Updated Dec 1, 2025 • 23.3k • 242 • 2

New activity in ospatch/QwQ-32B-INT8-W8A8 12 months ago

Woks 2x slower than GGUF q8

1

#2 opened 12 months ago by

plhf

New activity in ospatch/QwQ-32B-INT8-W8A8 about 1 year ago

Context length

1

#1 opened about 1 year ago by

matthew-at-qamcom

New activity in Qwen/QwQ-32B about 1 year ago

How to continue pt / sft on this model，any suggestions?

4

#53 opened about 1 year ago by

Ken0102030405

updated a model about 1 year ago

ospatch/QwQ-32B-INT8-W8A8

Text Generation • 33B • Updated Mar 13, 2025 • 45 • 5

liked a model about 1 year ago

Qwen/QwQ-32B

Text Generation • 33B • Updated Mar 11, 2025 • 67.5k • • 2.88k

published a model about 1 year ago

ospatch/QwQ-32B-INT8-W8A8

Text Generation • 33B • Updated Mar 13, 2025 • 45 • 5

liked a dataset over 1 year ago

rombodawg/Everything_Instruct

Viewer • Updated Oct 8, 2024 • 4.05M • 55 • 54

liked 2 models over 1 year ago

Qwen/Qwen2.5-72B-Instruct

Text Generation • 73B • Updated Jan 12, 2025 • 676k • • 923

google/gemma-2-27b-it

Text Generation • 27B • Updated Aug 27, 2024 • 296k • 561