Yang Chen

ychenNLP's activity

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

liked a model 3 months ago

deepseek-ai/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated Aug 1 • 4.32M • • 4.09k

liked a dataset 4 months ago

RUC-DataLab/CoDA-Bench

Viewer • Updated 26 days ago • 1.13k • 2.38k • 3

authored a paper 4 months ago

Unified Audio Intelligence Without Regressing on Text Intelligence

Paper • 2607.05196 • Published Jul 6 • 24

upvoted a paper 4 months ago

Unified Audio Intelligence Without Regressing on Text Intelligence

Paper • 2607.05196 • Published Jul 6 • 24

liked a model 4 months ago

nvidia/Nemotron-Labs-Audex-30B-A3B

Text Generation • Updated Aug 13 • 513 • 187

liked 2 models 5 months ago

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

Text Generation • 303B • Updated Aug 24 • 44.1k • • 366

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Text Generation • 561B • Updated Aug 24 • 1.13M • • 371

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 6 months ago

Cascade-2 cheating attempts on Math is... cute

👍🤯 4

3

#25 opened 7 months ago by

chankhavu

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 7 months ago

[Resolved] Unable to reproduce evals on AIME'25, AIME'26, HMMT Feb25

👀 2

7

#8 opened 7 months ago by

chankhavu

use system prompt for reasoning benchmarks reproduction (IMO-AnswerBench,..)

👍 2

#24 opened 7 months ago by

ychenNLP

liked a dataset 7 months ago

ychenNLP/oven

Updated Jul 1, 2024 • 1.94k • 17

liked a model 7 months ago

bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF

Text Generation • 32B • Updated Mar 22 • 7.19k • 47

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 7 months ago

187 tok/s on RTX 3090, 625K Context, Agent Coding (IQ4_XS + Hermes Agent)

🤯🔥 3

7

#20 opened 7 months ago by

ychenNLP

Official quantizations?

👍 2

6

#9 opened 7 months ago by

wijjjj

no quants working

2

#12 opened 7 months ago by

audioedge

pruned version

👀🔥 1

2

#16 opened 7 months ago by

pirola

Create jsjsj.py

2

#11 opened 7 months ago by

Kzksjzki828828

modeling_nemotron_h.py: Multiple bugs in HybridMambaAttentionDynamicCache break generation with CUDA fast path

2

#13 opened 7 months ago by

trohrbaugh

liked 2 models 7 months ago

chankhavu/Nemotron-Cascade-2-30B-A3B-NVFP4

Text Generation • 16B • Updated Mar 24 • 779 • 13

chankhavu/Nemotron-Cascade-2-30B-A3B-FP8

Text Generation • 32B • Updated Mar 24 • 65 • 1