| .. |
|
baby-llama
|
ab336a9d5e
code : normalize enum names (#5697)
|
1 anno fa |
|
batched
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
batched-bench
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
1 anno fa |
|
batched.swift
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
1 anno fa |
|
beam-search
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
benchmark
|
5b09797321
ggml : remove old quantization functions (#5942)
|
1 anno fa |
|
convert-llama2c-to-ggml
|
07cd41d096
TypoFix (#7162)
|
1 anno fa |
|
embedding
|
1b67731e18
BERT tokenizer fixes (#6498)
|
1 anno fa |
|
eval-callback
|
eaf4bd8b39
eval-callback : fix conversion to float (#7184)
|
1 anno fa |
|
export-lora
|
6e4e973b26
ci : add an option to fail on compile warning (#3952)
|
1 anno fa |
|
finetune
|
3855416027
ggml : introduce bfloat16 support (#6412)
|
1 anno fa |
|
gbnf-validator
|
cbaadc9294
grammars: 1.5x faster inference w/ complex grammars (vector reserves / reuses) (#6609)
|
1 anno fa |
|
gguf
|
8228b66dbc
gguf : add option to not check tensor data (#6582)
|
1 anno fa |
|
gguf-split
|
842500144e
gguf-split: add --no-tensor-first-split (#7072)
|
1 anno fa |
|
gritlm
|
8a56075b07
gritlm : add --outdir option to hf.sh script (#6699)
|
1 anno fa |
|
imatrix
|
48b2f9c1fc
Fixed save_imatrix to match old behaviour for MoE (#7099)
|
1 anno fa |
|
infill
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
jeopardy
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
2 anni fa |
|
llama-bench
|
628b299106
Adding support for the --numa argument for llama-bench. (#7080)
|
1 anno fa |
|
llama.android
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
llama.swiftui
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
1 anno fa |
|
llava
|
9da243b36a
Revert "llava : add support for moondream vision language model (#6899)"
|
1 anno fa |
|
lookahead
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
lookup
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
1 anno fa |
|
main
|
83330d8cd6
main : add --conversation / -cnv flag (#7108)
|
1 anno fa |
|
main-cmake-pkg
|
b8a7a5a90f
build(cmake): simplify instructions (`cmake -B build && cmake --build build ...`) (#6964)
|
1 anno fa |
|
parallel
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
passkey
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
perplexity
|
a8f9b07631
perplexity: more statistics, added documentation (#6936)
|
1 anno fa |
|
quantize
|
3855416027
ggml : introduce bfloat16 support (#6412)
|
1 anno fa |
|
quantize-stats
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
1 anno fa |
|
retrieval
|
64e7b47c69
examples : add "retrieval" (#6193)
|
1 anno fa |
|
save-load-state
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
1 anno fa |
|
server
|
f98eb31c51
convert-hf : save memory with lazy evaluation (#7075)
|
1 anno fa |
|
simple
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
speculative
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 anno fa |
|
sycl
|
04976db7a8
docs: fix typos (#7124)
|
1 anno fa |
|
tokenize
|
1b67731e18
BERT tokenizer fixes (#6498)
|
1 anno fa |
|
train-text-from-scratch
|
8b1b1f4982
train : add general name (#6752)
|
1 anno fa |
|
CMakeLists.txt
|
b804b1ef77
eval-callback: Example how to use eval callback for debugging (#6576)
|
1 anno fa |
|
Miku.sh
|
019fe257bb
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
|
2 anni fa |
|
alpaca.sh
|
a17a2683d8
alpaca.sh : update model file name (#2074)
|
2 anni fa |
|
base-translate.sh
|
96e80dabc6
examples : improve base-translate.sh script (#4783)
|
2 anni fa |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
2 anni fa |
|
chat-13B.sh
|
6daa09d879
examples : read chat prompts from a template file (#1196)
|
2 anni fa |
|
chat-persistent.sh
|
ac2219fef3
llama : fix session saving/loading (#3400)
|
2 anni fa |
|
chat-vicuna.sh
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
2 anni fa |
|
chat.sh
|
8341a25957
main : log file (#2748)
|
2 anni fa |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
2 anni fa |
|
json-schema-pydantic-example.py
|
5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
|
1 anno fa |
|
json_schema_to_grammar.py
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
1 anno fa |
|
llama.vim
|
125d03a503
llama.vim : added api key support (#5090)
|
2 anni fa |
|
llama2-13b.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 anni fa |
|
llama2.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 anni fa |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
2 anni fa |
|
make-ggml.py
|
ac43576124
make-ggml.py : compatibility with more models and GGUF (#3290)
|
2 anni fa |
|
pydantic-models-to-grammar-examples.py
|
d292f4f204
examples : make pydantic scripts pass mypy and support py3.8 (#5099)
|
2 anni fa |
|
pydantic_models_to_grammar.py
|
d292f4f204
examples : make pydantic scripts pass mypy and support py3.8 (#5099)
|
2 anni fa |
|
reason-act.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 anni fa |
|
regex-to-grammar.py
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
1 anno fa |
|
server-embd.py
|
2002bc96bf
server : refactor (#5882)
|
1 anno fa |
|
server-llama2-13B.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
2 anni fa |
|
ts-type-to-grammar.sh
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
1 anno fa |
slaren