| .. |
|
baby-llama
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
2 lat temu |
|
benchmark
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
2 lat temu |
|
embedding
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
jeopardy
|
5ddf7ea1fb
hooks : setting up flake8 and pre-commit hooks (#1681)
|
2 lat temu |
|
main
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
metal
|
90cc59d6ab
examples : fix examples/metal (#1920)
|
2 lat temu |
|
perplexity
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
quantize
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
quantize-stats
|
527b6fba1d
llama : make model stateless and context stateful (llama_state) (#1797)
|
2 lat temu |
|
save-load-state
|
527b6fba1d
llama : make model stateless and context stateful (llama_state) (#1797)
|
2 lat temu |
|
server
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
simple
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
train-text-from-scratch
|
eaa6ca5a61
ggml : increase max tensor name + clean up compiler warnings in train-text (#1988)
|
2 lat temu |
|
CMakeLists.txt
|
051e1b0e6a
llama : fix kv_cache `n` init (close #1903)
|
2 lat temu |
|
Miku.sh
|
a8a2efdc81
examples : various prompt and example fixes (#1298)
|
2 lat temu |
|
alpaca.sh
|
e9a9cb0c54
examples : Improve Alpaca Default Repeat Penalty: Better Match Alpaca.cpp Experience (#1107)
|
2 lat temu |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
2 lat temu |
|
chat-13B.sh
|
6daa09d879
examples : read chat prompts from a template file (#1196)
|
2 lat temu |
|
chat-persistent.sh
|
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564)
|
2 lat temu |
|
chat-vicuna.sh
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
2 lat temu |
|
chat.sh
|
79b2b266db
If n_predict == -1, generate forever
|
2 lat temu |
|
common.cpp
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
common.h
|
b853d45601
ggml : add NUMA support (#1556)
|
2 lat temu |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
2 lat temu |
|
reason-act.sh
|
a6956b25a1
add example of re-act pattern (#583)
|
2 lat temu |
David Yang
eaa6ca5a61
ggml : increase max tensor name + clean up compiler warnings in train-text (#1988)