Pavel Zloi

evilfreelancer's activity

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

upvoted a paper about 21 hours ago

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published 8 days ago • 199

updated 2 collections 8 days ago

Russian o1 / r1

Collection

Collection of LLMs specialized on Russian language tuned on o1 and r1 datasets. • 6 items • Updated 8 days ago

Tasks Decomposition

Collection

Collection of datasets where we can see decomposition of task solving, it may be useful for training reasoning models. • 3 items • Updated 8 days ago

liked 3 datasets 8 days ago

Lots-of-LoRAs/task168_strategyqa_question_decomposition

Viewer • Updated Dec 30, 2024 • 3.02k • 41 • 1

efederici/orca-math-decompositions

Viewer • Updated Apr 15, 2024 • 10.7k • 50 • 1

Sakib323/task-decomposition

Viewer • Updated Sep 9, 2024 • 2.32k • 39 • 1

updated a model 11 days ago

evilfreelancer/r1_yandexgpt5-lite_gguf

Updated 11 days ago • 223

published a model 11 days ago

evilfreelancer/r1_yandexgpt5-lite_gguf

Updated 11 days ago • 223

updated a model 11 days ago

evilfreelancer/r1_yandexgpt5-lite_lora

Text Generation • Updated 11 days ago • 21 • 1

published a model 11 days ago

evilfreelancer/r1_yandexgpt5-lite_lora

Text Generation • Updated 11 days ago • 21 • 1

liked 6 datasets 13 days ago

Vikhrmodels/russian_math

Viewer • Updated Jul 11, 2024 • 199 • 132 • 9

Pinkstack/thinking-multilingual-30-23-small-690

Viewer • Updated 12 days ago • 690 • 192 • 2

Vikhrmodels/reasoning-0.01-ru

Viewer • Updated Sep 24, 2024 • 29.9k • 119 • 9

rulins/DeepSeek-R1-Distill-Qwen-32B_NUMINA_train_amc_aime_merged_thoughts

Viewer • Updated Feb 3 • 3.64k • 40 • 1

lightblue/reasoning-multilingual-R1-Llama-70B-train

Viewer • Updated Jan 31 • 2.48k • 571 • 30

mizinovmv/ru_example_DeepSeek-R1-Distill-Qwen-32B

Viewer • Updated Jan 26 • 279 • 153 • 1

liked a Space 15 days ago

Running

1.13k

1.13k

Wan2.1

💻

Wan: Open and Advanced Large-Scale Video Generative Models