Jesse Gross
|
a103dae01e
runner.go: Only allocate 1 element embedding batches for mllama
|
6 hónapja |
Jesse Gross
|
26acdcf44e
runner.go: Don't set cross attention before sending embeddings
|
6 hónapja |
Jesse Gross
|
c826e57475
runner.go: Better abstract vision model integration
|
7 hónapja |
Daniel Hiltgen
|
712e99d477
Soften windows clang requirement (#7428)
|
6 hónapja |
Jesse Gross
|
de1557a0dc
runner.go: Better handle return NULL values from llama.cpp
|
7 hónapja |
Jesse Gross
|
03e40efa51
runner.go: Merge partial unicode characters before sending
|
7 hónapja |
Patrick Devine
|
c7cb0f0602
image processing for llama3.2 (#6963)
|
7 hónapja |
Gabe Goodhart
|
f2890a4494
IBM granite/granitemoe architecture support (#6760)
|
7 hónapja |
Jesse Gross
|
0077e22d52
runner.go: Handle truncation of tokens for stop sequences
|
7 hónapja |
Jeffrey Morgan
|
96efd9052f
Re-introduce the `llama` package (#5034)
|
7 hónapja |