| .. |
|
baby-llama
|
bc39553c90
build : enable more non-default compiler warnings (#3200)
|
%!s(int64=2) %!d(string=hai) anos |
|
batched
|
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
|
%!s(int64=2) %!d(string=hai) anos |
|
batched-bench
|
ef47ec18da
ggml : add ggml_soft_max_ext (#4256)
|
%!s(int64=2) %!d(string=hai) anos |
|
batched.swift
|
5c9f90cba1
swift : fix prompt tokenization logic (#4321)
|
%!s(int64=2) %!d(string=hai) anos |
|
beam-search
|
5be6c803fa
llama : remove token functions with `context` args in favor of `model` (#3720)
|
%!s(int64=2) %!d(string=hai) anos |
|
benchmark
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
%!s(int64=2) %!d(string=hai) anos |
|
convert-llama2c-to-ggml
|
8cf19d60dc
gguf : support big endian platform (#3552)
|
%!s(int64=2) %!d(string=hai) anos |
|
embedding
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
%!s(int64=2) %!d(string=hai) anos |
|
export-lora
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
%!s(int64=2) %!d(string=hai) anos |
|
finetune
|
0b871f1a04
finetune - update readme to mention llama support only (#4148)
|
%!s(int64=2) %!d(string=hai) anos |
|
gguf
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
%!s(int64=2) %!d(string=hai) anos |
|
infill
|
881800d1f0
main : Add ChatML functionality to main example (#4046)
|
%!s(int64=2) %!d(string=hai) anos |
|
jeopardy
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
%!s(int64=2) %!d(string=hai) anos |
|
llama-bench
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
%!s(int64=2) %!d(string=hai) anos |
|
llama.swiftui
|
d208995c6d
swift : fix concatenation method to avoid invalid UTF8 stringfication (#4325)
|
%!s(int64=2) %!d(string=hai) anos |
|
llava
|
33c9892af5
llava : ShareGPT4V compatibility (vision encoder only loading) (#4172)
|
%!s(int64=2) %!d(string=hai) anos |
|
lookahead
|
1f5cd83275
examples : add readme files
|
%!s(int64=2) %!d(string=hai) anos |
|
main
|
52c8bc3cf3
sampling : custom samplers order (#4285)
|
%!s(int64=2) %!d(string=hai) anos |
|
main-cmake-pkg
|
abd21fc99f
cmake : add missed dependencies (#3763)
|
%!s(int64=2) %!d(string=hai) anos |
|
metal
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
%!s(int64=2) %!d(string=hai) anos |
|
parallel
|
6b0a7420d0
llama : KV cache view API + better KV cache management (#4170)
|
%!s(int64=2) %!d(string=hai) anos |
|
perplexity
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
%!s(int64=2) %!d(string=hai) anos |
|
quantize
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
%!s(int64=2) %!d(string=hai) anos |
|
quantize-stats
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
%!s(int64=2) %!d(string=hai) anos |
|
save-load-state
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
%!s(int64=2) %!d(string=hai) anos |
|
server
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
%!s(int64=2) %!d(string=hai) anos |
|
simple
|
23b5e12eb5
simple : update error message for KV cache check (#4324)
|
%!s(int64=2) %!d(string=hai) anos |
|
speculative
|
da5eaef1f3
speculative : support `--color` (#4343)
|
%!s(int64=2) %!d(string=hai) anos |
|
tokenize
|
28a2e6e7d4
tokenize example: Respect normal add BOS token behavior (#4126)
|
%!s(int64=2) %!d(string=hai) anos |
|
train-text-from-scratch
|
81bc9214a3
train : fix #4227 (double free in examples/train-text-from-scratch/train-text-from-scratch.cpp) (#4351)
|
%!s(int64=2) %!d(string=hai) anos |
|
CMakeLists.txt
|
922754a8d6
lookahead : add example for lookahead decoding (#4207)
|
%!s(int64=2) %!d(string=hai) anos |
|
Miku.sh
|
019fe257bb
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
|
%!s(int64=2) %!d(string=hai) anos |
|
alpaca.sh
|
a17a2683d8
alpaca.sh : update model file name (#2074)
|
%!s(int64=2) %!d(string=hai) anos |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
%!s(int64=2) %!d(string=hai) anos |
|
chat-13B.sh
|
6daa09d879
examples : read chat prompts from a template file (#1196)
|
%!s(int64=2) %!d(string=hai) anos |
|
chat-persistent.sh
|
ac2219fef3
llama : fix session saving/loading (#3400)
|
%!s(int64=2) %!d(string=hai) anos |
|
chat-vicuna.sh
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
%!s(int64=2) %!d(string=hai) anos |
|
chat.sh
|
8341a25957
main : log file (#2748)
|
%!s(int64=2) %!d(string=hai) anos |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
%!s(int64=2) %!d(string=hai) anos |
|
json-schema-to-grammar.py
|
7c2227a197
chmod : make scripts executable (#2675)
|
%!s(int64=2) %!d(string=hai) anos |
|
llama.vim
|
2d7baaf50f
vim : streaming and more (#2495)
|
%!s(int64=2) %!d(string=hai) anos |
|
llama2-13b.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
%!s(int64=2) %!d(string=hai) anos |
|
llama2.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
%!s(int64=2) %!d(string=hai) anos |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
%!s(int64=2) %!d(string=hai) anos |
|
make-ggml.py
|
ac43576124
make-ggml.py : compatibility with more models and GGUF (#3290)
|
%!s(int64=2) %!d(string=hai) anos |
|
reason-act.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
%!s(int64=2) %!d(string=hai) anos |
|
server-llama2-13B.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
%!s(int64=2) %!d(string=hai) anos |
Georgi Gerganov
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)