| .. |
|
CMakeLists.txt
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
il y a 2 ans |
|
test-double-float.c
|
436e561931
all : be more strict about converting float to double (#458)
|
il y a 2 ans |
|
test-grad0.c
|
65bdd52a86
tests : sync test-grad0 from ggml
|
il y a 2 ans |
|
test-opt.c
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
il y a 2 ans |
|
test-quantize-fns.cpp
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
il y a 2 ans |
|
test-quantize-perf.cpp
|
a84ab1da8d
tests : fix quantize perf (#1990)
|
il y a 2 ans |
|
test-sampling.cpp
|
b061ba9e2a
llama : fix top-p sampling to match the canonical definition (#1953)
|
il y a 2 ans |
|
test-tokenizer-0.cpp
|
527b6fba1d
llama : make model stateless and context stateful (llama_state) (#1797)
|
il y a 2 ans |
katsu560
a84ab1da8d
tests : fix quantize perf (#1990)