Hiranya Jayathilaka
hiranya911
AI & ML interests
LLMs, Autonomous agents, Semantic search
Organizations
None yet
hiranya911's activity
OOM under vLLM even with 80GB GPU
5
#2 opened 11 months ago
by
mike-ravkine
always getting 0 in output
15
#3 opened 11 months ago
by
xubuild
How does this compare to ms-marco cross encoders?
3
#3 opened about 1 year ago
by
hiranya911
Normalizing embedding vectors
1
#17 opened over 1 year ago
by
hiranya911
Are these objects thread safe for concurrent use?
1
#21 opened over 1 year ago
by
hiranya911
Any guidelines on composing instructions?
1
#8 opened over 1 year ago
by
hiranya911
Max tokens
5
#5 opened over 1 year ago
by
hiranya911
Max tokens
5
#5 opened over 1 year ago
by
hiranya911