Ollama template
1
#6 opened 4 days ago
by
yqchen-sci
A low number of evaluation benchmarks
1
#5 opened 5 days ago
by
Michalea
Failed to initialize the context: quantized V cache was requested, but this requires Flash Attention
2
#4 opened 6 days ago
by
SilverJim
The generation falls into constant repetition without any good result
9
#2 opened 10 days ago
by
ddd2r2
Performance is poor
11
#1 opened 11 days ago
by
sainnhe