| .. |
|
baby-llama
|
ef15649972
build : fix most gcc and clang warnings (#2861)
|
2 vuotta sitten |
|
beam-search
|
ef15649972
build : fix most gcc and clang warnings (#2861)
|
2 vuotta sitten |
|
benchmark
|
b1f4290953
cmake : install targets (#2256)
|
2 vuotta sitten |
|
convert-llama2c-to-ggml
|
0d58936686
llama2c : rename function
|
2 vuotta sitten |
|
embd-input
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 vuotta sitten |
|
embedding
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 vuotta sitten |
|
gguf
|
44c117f41e
train : mem usage and other improvements (#2439)
|
2 vuotta sitten |
|
gptneox-wip
|
c42f0ec6b3
examples : fix gpt-neox (#2943)
|
2 vuotta sitten |
|
jeopardy
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 vuotta sitten |
|
llama-bench
|
43033b7bb4
llama-bench : set locale to utf8 (#2832)
|
2 vuotta sitten |
|
main
|
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
|
2 vuotta sitten |
|
metal
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 vuotta sitten |
|
perplexity
|
fa3582f509
Tell users attmepting to run perplexity with too few tokens to use more (#2882)
|
2 vuotta sitten |
|
quantize
|
5d6f19f16b
Allow quantize to only copy tensors, some other improvements (#2931)
|
2 vuotta sitten |
|
quantize-stats
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 vuotta sitten |
|
save-load-state
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 vuotta sitten |
|
server
|
e4386f417f
server : add a subtle loading animation to the edit box (#2466)
|
2 vuotta sitten |
|
simple
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 vuotta sitten |
|
speculative
|
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
|
2 vuotta sitten |
|
train-text-from-scratch
|
aeefac4ff7
scripts: Use local gguf package when running from repo (#2927)
|
2 vuotta sitten |
|
CMakeLists.txt
|
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
|
2 vuotta sitten |
|
Miku.sh
|
019fe257bb
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
|
2 vuotta sitten |
|
alpaca.sh
|
a17a2683d8
alpaca.sh : update model file name (#2074)
|
2 vuotta sitten |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
2 vuotta sitten |
|
chat-13B.sh
|
6daa09d879
examples : read chat prompts from a template file (#1196)
|
2 vuotta sitten |
|
chat-persistent.sh
|
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564)
|
2 vuotta sitten |
|
chat-vicuna.sh
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
2 vuotta sitten |
|
chat.sh
|
8341a25957
main : log file (#2748)
|
2 vuotta sitten |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
2 vuotta sitten |
|
json-schema-to-grammar.py
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 vuotta sitten |
|
llama.vim
|
2d7baaf50f
vim : streaming and more (#2495)
|
2 vuotta sitten |
|
llama2-13b.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 vuotta sitten |
|
llama2.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 vuotta sitten |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
2 vuotta sitten |
|
make-ggml.py
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 vuotta sitten |
|
reason-act.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 vuotta sitten |
|
server-llama2-13B.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 vuotta sitten |
Aarni Koskela
e4386f417f
server : add a subtle loading animation to the edit box (#2466)