Jesse Gross
|
854a9195f3
attention: Remove unnecessary contiguous operations
|
há 2 meses atrás |
Michael Yang
|
53d2990d9b
model: add bos token if configured
|
há 2 meses atrás |
Jesse Gross
|
f53f4198c3
ml: Abstract attention out of model definitions
|
há 2 meses atrás |
Jesse Gross
|
5c5535c064
models: Prune unused outputs earlier in the forward pass
|
há 2 meses atrás |
Jesse Gross
|
ed443a0393
Runner for Ollama engine
|
há 4 meses atrás |
Jesse Gross
|
6945617af5
models: Move model into their own directory
|
há 2 meses atrás |