mengfanxu
fxmeng
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
On the Design of Hyper-Connections: Simplification, Stability, and Scalability updated a collection 28 days ago
LatentIndex updated a collection 28 days ago
LatentIndexOrganizations
None yet
models 59
fxmeng/DSV2-Lite-LatentIndex-Sparse-1250
Text Generation • Updated • 422
fxmeng/DSV2-Lite-IndexCache-Sparse-1250
Text Generation • Updated • 411
fxmeng/DSV2-Lite-DSA-Sparse-1250
Text Generation • Updated • 154
fxmeng/DSV2-Lite-IndexCache-Warmup-400
Text Generation • Updated • 85
fxmeng/DSV2-Lite-LatentIndex-Warmup-400
Text Generation • Updated • 85
fxmeng/DSV2-Lite-DSA-Warmup-400
Text Generation • Updated • 95
fxmeng/TransMLA-llama3-8b-32k
8B • Updated • 37
fxmeng/TransMLA-llama3-8b-8k
8B • Updated • 25
fxmeng/PiSSA-llama-7b-commonsense-148k
7B • Updated • 16
fxmeng/PiSSA-Llama-3-8b-commonsense-148k
8B • Updated • 16
datasets 14
fxmeng/UltraData-SFT-2605-no-think-8k-32k
Viewer • Updated • 947k • 480
fxmeng/UltraData-SFT-2605-no-think-32k-200k
Viewer • Updated • 17.6k • 231
fxmeng/transmla_pretrain_100m_tokens
Viewer • Updated • 100k • 32
fxmeng/transmla_pretrain_1B_tokens
Viewer • Updated • 1.14M • 339
fxmeng/transmla_pretrain_6B_tokens
Viewer • Updated • 5.94M • 640
fxmeng/pissa-dataset
Viewer • Updated • 844k • 1.74k • 3
fxmeng/big-bench-hard-continue-finetuning
Viewer • Updated • 10.3k • 138 • 1
fxmeng/commonsense_filtered
Viewer • Updated • 170k • 151 • 1
fxmeng/MetaMath-GSM240K
Viewer • Updated • 240k • 58 • 1
fxmeng/MetaMath-MATH155K
Viewer • Updated • 155k • 40