SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models
Paper
•
2410.03750
•
Published
•
1
AI & ML interests
None defined yet.
Recent Activity
View all activity
IntelLabs's activity
jinjieyuan
authored
4
papers
6 days ago
Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models
Paper
•
2501.17088
•
Published
•
1
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
Paper
•
2111.00653
•
Published
MultiPruner: Balanced Structure Removal in Foundation Models
Paper
•
2501.09949
•
Published
jinjieyuan
updated
16
models
7 days ago
IntelLabs/lonas-bloomz-7b-math
Updated
•
3
IntelLabs/lonas-bert-base-glue
Updated
•
3
IntelLabs/lonas-llama-7b-commonsense-adapter
Updated
•
4
IntelLabs/sqft-mistral-7b-v0.3-50-base
Text Generation
•
Updated
•
198
•
2
IntelLabs/shears-llama-7b-50-math-heuristic-adapter
Updated
•
15
•
3
IntelLabs/shears-llama-7b-50-math-super-adapter
Updated
•
10
•
3
IntelLabs/shears-mpt-7b-50-gsm8k-heuristic-adapter
Updated
•
128
•
3
IntelLabs/shears-mpt-7b-50-gsm8k-super-adapter
Updated
•
10
•
3
IntelLabs/shears-llama-13b-50-math-heuristic-adapter
Updated
•
13
•
3
IntelLabs/shears-mpt-7b-50-base
Text Generation
•
Updated
•
71
•
2
IntelLabs/shears-llama-13b-50-math-super-adapter
Updated
•
9
•
4
IntelLabs/shears-llama-7b-50-cs-heuristic-adapter
Updated
•
6
•
3
IntelLabs/shears-llama-7b-50-cs-super-adapter
Updated
•
5
•
3
IntelLabs/sqft-phi-3.5-mini-instruct-base-gptq
Text Generation
•
Updated
•
242
•
3
IntelLabs/sqft-sparsepeft-phi-3-mini-4k-60-math-heu
Text Generation
•
Updated
•
171
•
1
IntelLabs/sqft-sparsepeft-phi-3-mini-4k-40-math-heu
Text Generation
•
Updated
•
170
•
1