| .. |
|
baby-llama
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
il y a 2 ans |
|
benchmark
|
ec2e10c444
llama : add llama_init_backend() API (close #1527)
|
il y a 2 ans |
|
embedding
|
ec2e10c444
llama : add llama_init_backend() API (close #1527)
|
il y a 2 ans |
|
jeopardy
|
5fba3c016b
examples : add Jeopardy example (#1168)
|
il y a 2 ans |
|
main
|
35a84916fb
main: add the possibility to open the prompt cache read-only (#1640)
|
il y a 2 ans |
|
metal
|
ecb217db4f
llama : Metal inference (#1642)
|
il y a 2 ans |
|
perplexity
|
ec2e10c444
llama : add llama_init_backend() API (close #1527)
|
il y a 2 ans |
|
quantize
|
4f0154b0ba
llama : support requantizing models instead of only allowing quantization from 16/32bit (#1691)
|
il y a 2 ans |
|
quantize-stats
|
99009e72f8
ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684)
|
il y a 2 ans |
|
save-load-state
|
dc271c52ed
Remove unused n_parts parameter (#1509)
|
il y a 2 ans |
|
server
|
17366df842
Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
|
il y a 2 ans |
|
CMakeLists.txt
|
ecb217db4f
llama : Metal inference (#1642)
|
il y a 2 ans |
|
Miku.sh
|
a8a2efdc81
examples : various prompt and example fixes (#1298)
|
il y a 2 ans |
|
alpaca.sh
|
e9a9cb0c54
examples : Improve Alpaca Default Repeat Penalty: Better Match Alpaca.cpp Experience (#1107)
|
il y a 2 ans |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
il y a 2 ans |
|
chat-13B.sh
|
6daa09d879
examples : read chat prompts from a template file (#1196)
|
il y a 2 ans |
|
chat-persistent.sh
|
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564)
|
il y a 2 ans |
|
chat.sh
|
79b2b266db
If n_predict == -1, generate forever
|
il y a 2 ans |
|
common.cpp
|
35a84916fb
main: add the possibility to open the prompt cache read-only (#1640)
|
il y a 2 ans |
|
common.h
|
35a84916fb
main: add the possibility to open the prompt cache read-only (#1640)
|
il y a 2 ans |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
il y a 2 ans |
|
reason-act.sh
|
a6956b25a1
add example of re-act pattern (#583)
|
il y a 2 ans |
Kerfuffle
4f0154b0ba
llama : support requantizing models instead of only allowing quantization from 16/32bit (#1691)