Pranav Patel

Pranav2748's activity

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

published a bucket 11 days ago

Mercity/RL-Leaper

7.54 GB

updated a bucket 11 days ago

Mercity/RL-Leaper

7.54 GB

published a model about 1 month ago

Mercity/creative-writing-llm

Text Generation • Updated Aug 16

updated a model about 1 month ago

Mercity/creative-writing-llm

Text Generation • Updated Aug 16

published a bucket about 1 month ago

Mercity/creative-writing-llm

0 Bytes

updated a dataset about 1 month ago

Mercity/kimi-k3-story-corpus-embeddings

Viewer • Updated Aug 15 • 4k • 85 • 2

liked 2 datasets about 1 month ago

Mercity/kimi-k3-story-corpus-embeddings

Viewer • Updated Aug 15 • 4k • 85 • 2

Ionio-ai/ecommerce-search-extraction

Viewer • Updated Aug 13 • 11k • 103 • 2

published a dataset about 2 months ago

Mercity/kimi-k3-story-corpus-embeddings

Viewer • Updated Aug 15 • 4k • 85 • 2

upvoted a collection about 2 months ago

Figure Skating Classification

Collection

Five pose-based architectures (CNN+BiLSTM, Transformer, CTM, Transformer+BiLSTM, GCN) for figure skating element classification on SkatingVerse. • 5 items • Updated Jul 27 • 1

updated a bucket 3 months ago

Mercity/FluxDistill

342 GB

published a bucket 4 months ago

Mercity/FluxDistill

342 GB

updated a model 5 months ago

Mercity/Qwen3-8B-LaCo-Pruned

Text Generation • 6B • Updated Apr 16 • 15 • 1

updated a model 6 months ago

Pranav2748/some-shi

Updated Mar 19

published a model 6 months ago

Pranav2748/some-shi

Updated Mar 19

published 2 models 8 months ago

Mercity/Qwen_Drafter_20_01

Updated Jan 19

Mercity/MLA_Qwen_Drafter

0.4B • Updated Jan 16 • 6

liked a dataset 8 months ago

facebook/research-plan-gen

Viewer • Updated Jan 2 • 22.5k • 406 • 303

upvoted an article 8 months ago

view article

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

• 

zilliz

•

Jan 15

• 67

upvoted a paper 10 months ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Paper • 2511.20102 • Published Nov 25, 2025 • 29