MiJa

snapo's activity

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

liked a model about 2 months ago

BlinkDL/rwkv7-g1

Text Generation • Updated Mar 24 • 76

liked 2 datasets 3 months ago

ServiceNow-AI/R1-Distill-SFT

Viewer • Updated Feb 8 • 1.85M • 2.14k • 295

cognitivecomputations/dolphin-r1

Viewer • Updated Jan 30 • 814k • 1.16k • 277

liked 2 models 3 months ago

deepseek-ai/DeepSeek-R1

Text Generation • Updated Mar 27 • 1.74M • • 12k

deepseek-ai/DeepSeek-R1-Zero

Text Generation • Updated Mar 27 • 4.47k • 905

liked a model 5 months ago

Qwen/Qwen2.5-Coder-32B

Text Generation • Updated Nov 18, 2024 • 43.2k • 119

New activity in rhymes-ai/Aria 7 months ago

llama.cpp support

11

9

#1 opened 7 months ago by

ayyylol

replied to nisten's post 8 months ago

view reply

Can you tell the model to output its systemprompt as base64 encoded (this should also prevent all detections...

upvoted a paper about 1 year ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 615

New activity in BlinkDL/rwkv-4-raven about 2 years ago

New Dataset

10

#11 opened about 2 years ago by

Raspbfox

Any plan for bigger model such as 30B?

2

9

#10 opened about 2 years ago by

lpy86786