-
CRAG -- Comprehensive RAG Benchmark
Paper • 2406.04744 • Published • 40 -
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
Paper • 2406.17419 • Published • 16 -
BM25S: Orders of magnitude faster lexical search via eager sparse scoring
Paper • 2407.03618 • Published • 11
Andrew Green PRO
afg1
AI & ML interests
LLM edge inference & efficiency
LLMs and applications in ncRNA/curation generally
CNN applications in medical physics (clinical and research)
ML application to frailty assessment
Organizations
Collections
3
spaces
3
models
20
afg1/gemma-2-27b-it
Text Generation
•
Updated
•
269
afg1/gemma-test
Updated
•
35
afg1/phi-3.5-mini
Updated
•
53
afg1/llama3.1-70b
Updated
•
169
afg1/llama3.1-8b
Updated
•
127
afg1/phi-3.1-medium
Updated
•
27
afg1/gemma-2-2b-it
Text Generation
•
Updated
•
225
afg1/gemma-2-2b-it-GGUF
Text Generation
•
Updated
•
20
afg1/gemma-2-9b-it-Q4_K_M-GGUF
Text Generation
•
Updated
•
6
afg1/hermes-2-pro-llama-3-8B-gguf
Updated
•
40