| .. |
|
baby-llama
|
bc39553c90
build : enable more non-default compiler warnings (#3200)
|
il y a 2 ans |
|
batched
|
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
|
il y a 2 ans |
|
batched-bench
|
6e08281e58
Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)
|
il y a 2 ans |
|
batched.swift
|
0e89203b51
speculative : add tree-based sampling example (#3624)
|
il y a 2 ans |
|
beam-search
|
5be6c803fa
llama : remove token functions with `context` args in favor of `model` (#3720)
|
il y a 2 ans |
|
benchmark
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
convert-llama2c-to-ggml
|
8cf19d60dc
gguf : support big endian platform (#3552)
|
il y a 2 ans |
|
embedding
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
export-lora
|
0e76a8992c
train : finetune LORA (#2632)
|
il y a 2 ans |
|
finetune
|
e9c1cecb9d
ggml : fix backward rope after YaRN (#3974)
|
il y a 2 ans |
|
gguf
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
il y a 2 ans |
|
infill
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
jeopardy
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
il y a 2 ans |
|
llama-bench
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
llava
|
54b4df8886
Use params when loading models in llava-cli (#3976)
|
il y a 2 ans |
|
main
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
main-cmake-pkg
|
abd21fc99f
cmake : add missed dependencies (#3763)
|
il y a 2 ans |
|
metal
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
il y a 2 ans |
|
parallel
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
perplexity
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
quantize
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
quantize-stats
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
save-load-state
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
server
|
57ad015dc3
server : add min_p param (#3877)
|
il y a 2 ans |
|
simple
|
c8d6a1f34a
simple : fix batch handling (#3803)
|
il y a 2 ans |
|
speculative
|
8f961abdc4
speculative : change default p_accept to 0.5 + CLI args (#3919)
|
il y a 2 ans |
|
train-text-from-scratch
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
il y a 2 ans |
|
CMakeLists.txt
|
d1031cf49c
sampling : refactor init to use llama_sampling_params (#3696)
|
il y a 2 ans |
|
Miku.sh
|
019fe257bb
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
|
il y a 2 ans |
|
alpaca.sh
|
a17a2683d8
alpaca.sh : update model file name (#2074)
|
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
|
ac2219fef3
llama : fix session saving/loading (#3400)
|
il y a 2 ans |
|
chat-vicuna.sh
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
il y a 2 ans |
|
chat.sh
|
8341a25957
main : log file (#2748)
|
il y a 2 ans |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
il y a 2 ans |
|
json-schema-to-grammar.py
|
7c2227a197
chmod : make scripts executable (#2675)
|
il y a 2 ans |
|
llama.vim
|
2d7baaf50f
vim : streaming and more (#2495)
|
il y a 2 ans |
|
llama2-13b.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
il y a 2 ans |
|
llama2.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
il y a 2 ans |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
il y a 2 ans |
|
make-ggml.py
|
ac43576124
make-ggml.py : compatibility with more models and GGUF (#3290)
|
il y a 2 ans |
|
reason-act.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
il y a 2 ans |
|
server-llama2-13B.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
il y a 2 ans |
Mihai
57ad015dc3
server : add min_p param (#3877)