Roman yemelyanov

Roman1111111's activity

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

New activity in TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF about 7 hours ago

how do you fine tune?

👀 4

56

#8 opened 7 days ago by

Roman1111111

New activity in prefeitura-rio/Rio-2.5-Open 3 days ago

wow, what dataset do you use to train?

6

#1 opened 4 days ago by

Roman1111111

New activity in Nanbeige/Nanbeige4.1-3B 4 days ago

dataset for sft

1

#30 opened 4 days ago by

Roman1111111

liked 3 models 4 days ago

prefeitura-rio/Rio-3.0-Open

Text Generation • 235B • Updated 15 days ago • 23 • 3

prefeitura-rio/Rio-2.5-Open

Text Generation • 31B • Updated 15 days ago • 21 • 3

Daemontatox/HydraMind

Text Generation • 31B • Updated Aug 1, 2025 • 6 • 5

New activity in Daemontatox/HydraMind 4 days ago

benchmarks

👍 1

#1 opened 4 days ago by

Roman1111111

New activity in reedmayhew/gemini-3.1-pro-distill-reasoning-12B-QKVO-GGUF 4 days ago

model card

1

#1 opened 4 days ago by

Roman1111111

liked a model 4 days ago

MuXodious/Nanbeige4.1-3B-PaperWitch-heresy

Text Generation • 4B • Updated 7 days ago • 44 • 3

New activity in MuXodious/Nanbeige4.1-3B-PaperWitch-heresy 4 days ago

that low kl difference!!?

🤝 1

3

#2 opened 4 days ago by

Roman1111111

liked a Space 5 days ago

Running on Zero

2

Nanochat-chat-finetuned

🌍

2

Chat with a fast AI assistant

New activity in ernie-research/MEnvData-SWE-Trajectory 5 days ago

Effect on the llms

4

#2 opened 11 days ago by

Roman1111111

liked a dataset 5 days ago

Roman1111111/gemini-3.1-pro-hard-high-reasoning

Viewer • Updated 5 days ago • 3.15k • 69 • 4

updated a dataset 5 days ago

Roman1111111/gemini-3.1-pro-hard-high-reasoning

Viewer • Updated 5 days ago • 3.15k • 69 • 4

published a dataset 6 days ago

Roman1111111/gemini-3.1-pro-hard-high-reasoning

Viewer • Updated 5 days ago • 3.15k • 69 • 4

published a dataset 7 days ago

Roman1111111/gemini-3-flash-120000x-high-reasoning

Updated 7 days ago • 8 • 1

updated a dataset 7 days ago

Roman1111111/gemini-3-pro-10000x-hard-high-reasoning

Viewer • Updated 7 days ago • 10k • 334 • 11

liked a dataset 7 days ago

Roman1111111/gemini-3-pro-10000x-hard-high-reasoning

Viewer • Updated 7 days ago • 10k • 334 • 11

published a dataset 8 days ago

Roman1111111/gemini-3-pro-10000x-hard-high-reasoning

Viewer • Updated 7 days ago • 10k • 334 • 11

liked a dataset 11 days ago

crownelius/GLM-5.0-25000x

Viewer • Updated 14 days ago • 26.1k • 146 • 8