Pretraining Context Compressor for Large Language Models with Embedding-Based Memory
YuHong Dai
BroAlanTaps
AI & ML interests
CV(2D-Object Detection), NLP(Infer Accelerate)
Recent Activity
upvoted a collection 4 days ago
Qwen3.5 liked
a model 18 days ago
stepfun-ai/Step-3.5-Flash authored
a paper
18 days ago
GEBench: Benchmarking Image Generation Models as GUI Environments Organizations
models 123
BroAlanTaps/wikipedia-visual-en-qwen2.5-2b-instruct-lora-sft-wikipedia-samples
Image-Text-to-Text • 2B • Updated
BroAlanTaps/Stage2-PCC-Large-16x
Updated
BroAlanTaps/Stage2-PCC-Large-128x
Updated
BroAlanTaps/Stage2-PCC-Large-4x
Updated
BroAlanTaps/PCC-Large-Encoder-Llama3-8B-Instruct
8B • Updated
BroAlanTaps/Stage1-PCC-Large-128x
Updated
BroAlanTaps/Stage2-PCC-Lite-256x
0.8B • Updated
BroAlanTaps/Stage2-PCC-Lite-128x
0.8B • Updated
• 1
BroAlanTaps/Stage2-PCC-Lite-64x
0.8B • Updated
BroAlanTaps/Stage2-PCC-Lite-16x
0.8B • Updated
• 1
datasets 7
BroAlanTaps/Warmup-GPT2-Large-Llama3-8B-Redpajama
Viewer
• Updated
• 1.55M • 16
BroAlanTaps/pretrain-corpus-test
Viewer
• Updated
• 576 • 82
BroAlanTaps/GPT2-Large-Llama3-8B-fineweb-256-5Btokens
Viewer
• Updated
• 19.2M • 19
BroAlanTaps/efficiency_samples_8k
Viewer
• Updated
• 1k • 4
BroAlanTaps/Stage2-PCC-Large-SFT-Squad
Viewer
• Updated
• 92.7k • 12
BroAlanTaps/Stage2-PCC-SFT-HotpotQA
Viewer
• Updated
• 90.4k • 124
BroAlanTaps/Stage2-PCC-Lite-SFT-Squad
Viewer
• Updated
• 92.7k • 215