| .. |
|
baby-llama
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 jaar geleden |
|
batched
|
da3913d8f9
batched: fix n_predict parameter (#8527)
|
1 jaar geleden |
|
batched-bench
|
ecf6b7f23e
batched-bench : handle empty `-npl` (#8839)
|
1 jaar geleden |
|
batched.swift
|
213701b51a
Detokenizer fixes (#8039)
|
1 jaar geleden |
|
benchmark
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 jaar geleden |
|
convert-llama2c-to-ggml
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
cvector-generator
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 jaar geleden |
|
deprecation-warning
|
be6d7c0791
examples : remove `finetune` and `train-text-from-scratch` (#8669)
|
1 jaar geleden |
|
embedding
|
7c3f55c100
Add support for encoder-only T5 models (#8900)
|
1 jaar geleden |
|
eval-callback
|
4af8420afb
common : remove duplicate function llama_should_add_bos_token (#8778)
|
1 jaar geleden |
|
export-lora
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 jaar geleden |
|
gbnf-validator
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
1 jaar geleden |
|
gguf
|
07283b1a90
gguf : handle null name during init (#8587)
|
1 jaar geleden |
|
gguf-hash
|
1666f92dcd
gguf-hash : update clib.json to point to original xxhash repo (#8491)
|
1 jaar geleden |
|
gguf-split
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
gritlm
|
80ea089d77
llama : allow pooled embeddings on any model (#7477)
|
1 jaar geleden |
|
imatrix
|
4af8420afb
common : remove duplicate function llama_should_add_bos_token (#8778)
|
1 jaar geleden |
|
infill
|
4af8420afb
common : remove duplicate function llama_should_add_bos_token (#8778)
|
1 jaar geleden |
|
jeopardy
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
llama-bench
|
bdf314f38a
llama-bench : fix NUL terminators in CPU name (#9313)
|
1 jaar geleden |
|
llama.android
|
b7c11d36e6
examples: fix android example cannot be generated continuously (#8621)
|
1 jaar geleden |
|
llama.swiftui
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 jaar geleden |
|
llava
|
7ea8d80d53
llava : the function "clip" should be int (#9237)
|
1 jaar geleden |
|
lookahead
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
1 jaar geleden |
|
lookup
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
1 jaar geleden |
|
main
|
b60074f1c2
llama-cli : remove duplicated log message (#9275)
|
1 jaar geleden |
|
main-cmake-pkg
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 jaar geleden |
|
parallel
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
1 jaar geleden |
|
passkey
|
61ecafa390
passkey : add short intro to README.md [no-ci] (#8317)
|
1 jaar geleden |
|
perplexity
|
4af8420afb
common : remove duplicate function llama_should_add_bos_token (#8778)
|
1 jaar geleden |
|
quantize
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 jaar geleden |
|
quantize-stats
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 jaar geleden |
|
retrieval
|
4b9afbbe90
retrieval : fix memory leak in retrieval query handling (#8955)
|
1 jaar geleden |
|
rpc
|
b72942fac9
Merge commit from fork
|
1 jaar geleden |
|
save-load-state
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
1 jaar geleden |
|
server
|
48baa61ecc
server : test script : add timeout for all requests (#9282)
|
1 jaar geleden |
|
simple
|
5f4dcb1e60
simple : update name of executable to llama-simple (#8885)
|
1 jaar geleden |
|
speculative
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 jaar geleden |
|
sycl
|
0478174d59
[SYCL] Updated SYCL device filtering (#8901)
|
1 jaar geleden |
|
tokenize
|
4af8420afb
common : remove duplicate function llama_should_add_bos_token (#8778)
|
1 jaar geleden |
|
CMakeLists.txt
|
be6d7c0791
examples : remove `finetune` and `train-text-from-scratch` (#8669)
|
1 jaar geleden |
|
Miku.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
base-translate.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
2 jaren geleden |
|
chat-13B.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
chat-persistent.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
chat-vicuna.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
chat.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
convert_legacy_llama.py
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
1 jaar geleden |
|
json_schema_pydantic_example.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 jaar geleden |
|
json_schema_to_grammar.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 jaar geleden |
|
llama.vim
|
125d03a503
llama.vim : added api key support (#5090)
|
2 jaren geleden |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
2 jaren geleden |
|
pydantic_models_to_grammar.py
|
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
|
1 jaar geleden |
|
pydantic_models_to_grammar_examples.py
|
22f281aa16
examples : Rewrite pydantic_models_to_grammar_examples.py (#8493)
|
1 jaar geleden |
|
reason-act.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
regex_to_grammar.py
|
e235b267a2
py : switch to snake_case (#8305)
|
1 jaar geleden |
|
server-llama2-13B.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 jaar geleden |
|
server_embd.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 jaar geleden |
|
ts-type-to-grammar.sh
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
1 jaar geleden |
compilade
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)