-
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
SPLADE-v3: New baselines for SPLADE
Paper • 2403.06789 • Published • 5 -
MMTEB: Massive Multilingual Text Embedding Benchmark
Paper • 2502.13595 • Published • 41 -
Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
Paper • 2409.14683 • Published • 12
Abdulhakeem Adefioye
kokolamba
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
ReplaceMe: Network Simplification via Layer Pruning and Linear
Transformations
updated
a model
7 days ago
kokolamba/moe-mha
Organizations
-
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
SPLADE-v3: New baselines for SPLADE
Paper • 2403.06789 • Published • 5 -
MMTEB: Massive Multilingual Text Embedding Benchmark
Paper • 2502.13595 • Published • 41 -
Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
Paper • 2409.14683 • Published • 12
models
29
kokolamba/moe-mha
Updated
•
17
kokolamba/moe-kv-128
Updated
•
17
kokolamba/moe-o-192
Updated
•
11
kokolamba/SubspaceDecoder_mha
Updated
•
51
kokolamba/SubspaceDecoder_mla192-0-0
Updated
•
28
kokolamba/SubspaceDecoder_mla0-0-0
Updated
kokolamba/SubspaceDecoder_mla0-0-192
Updated
•
33
kokolamba/SubspaceDecoder_mla0-96-192
Updated
•
33
kokolamba/SubspaceDecoder_mla0-128-0
Updated
•
27
kokolamba/SubspaceDecoder_mla192-96-192
Updated
•
31